< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 22 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3818. Min Act: -0.0004

Data Index: 841012 (The Pile)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3621. Min Act: -0.0004

Data Index: 802259 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3062. Min Act: -0.0004

Data Index: 1629186 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3150. Min Act: -0.0004

Data Index: 1080648 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2957. Min Act: -0.0004

Data Index: 1425411 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2950. Min Act: -0.0004

Data Index: 1741818 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2956. Min Act: -0.0004

Data Index: 1089050 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2822. Min Act: -0.0004

Data Index: 1467292 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2903. Min Act: -0.0004

Data Index: 272142 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2876. Min Act: -0.0004

Data Index: 779379 (The Pile)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2889. Min Act: -0.0004

Data Index: 511827 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2786. Min Act: -0.0004

Data Index: 265489 (The Pile)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2863. Min Act: -0.0004

Data Index: 231998 (The Pile)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2934. Min Act: -0.0004

Data Index: 1422111 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2710. Min Act: -0.0004

Data Index: 353623 (The Pile)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2814. Min Act: -0.0004

Data Index: 1116940 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2804. Min Act: -0.0004

Data Index: 1440249 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2694. Min Act: -0.0004

Data Index: 1760663 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2790. Min Act: -0.0004

Data Index: 379739 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2762. Min Act: -0.0004

Data Index: 549868 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #19