< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4086 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.4175. Min Act: -0.0001

Data Index: 1160116 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.4202. Min Act: -0.0001

Data Index: 932280 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3579. Min Act: -0.0001

Data Index: 916815 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3942. Min Act: -0.0001

Data Index: 403243 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1734502 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3932. Min Act: -0.0001

Data Index: 1379119 (The Pile)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3262. Min Act: -0.0001

Data Index: 1767095 (The Pile)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3415. Min Act: -0.0001

Data Index: 1751772 (The Pile)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3713. Min Act: -0.0001

Data Index: 728448 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3450. Min Act: -0.0001

Data Index: 740992 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3098. Min Act: -0.0001

Data Index: 11617 (The Pile)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3130. Min Act: -0.0001

Data Index: 600582 (The Pile)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3500. Min Act: -0.0001

Data Index: 1453249 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3262. Min Act: -0.0001

Data Index: 784812 (The Pile)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3938. Min Act: -0.0001

Data Index: 525818 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3589. Min Act: -0.0001

Data Index: 1028208 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3061. Min Act: -0.0001

Data Index: 1619039 (The Pile)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3071. Min Act: -0.0001

Data Index: 635198 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3236. Min Act: -0.0001

Data Index: 344405 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1279117 (The Pile)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #19