< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4069 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.1196. Min Act: -0.0001

Data Index: 791094 (The Pile)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.0422. Min Act: -0.0001

Data Index: 1893026 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.1139. Min Act: -0.0001

Data Index: 404653 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9298. Min Act: -0.0001

Data Index: 1329583 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9238. Min Act: -0.0001

Data Index: 1128559 (The Pile)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.1044. Min Act: -0.0001

Data Index: 1290888 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.8941. Min Act: -0.0001

Data Index: 490216 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1052903 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.8152. Min Act: -0.0001

Data Index: 562378 (The Pile)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1639679 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.8465. Min Act: -0.0001

Data Index: 1597806 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.8808. Min Act: -0.0001

Data Index: 360094 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.7647. Min Act: -0.0001

Data Index: 617740 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9327. Min Act: -0.0001

Data Index: 1549090 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.8484. Min Act: -0.0001

Data Index: 276616 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.8443. Min Act: -0.0001

Data Index: 923476 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.8006. Min Act: -0.0000

Data Index: 522167 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.7609. Min Act: -0.0001

Data Index: 1997620 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.8055. Min Act: -0.0001

Data Index: 540534 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.7239. Min Act: -0.0001

Data Index: 993932 (The Pile)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #19