Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4710 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1971391 (The Pile)

Max Activating Token Index: 922

Text #1

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.4230. Min Act: -0.0000

Data Index: 154490 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1723877 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1443794 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1445329 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3537. Min Act: -0.0000

Data Index: 725495 (The Pile)

Max Activating Token Index: 514

Text #6

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1346754 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3216. Min Act: -0.0000

Data Index: 558536 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3536. Min Act: -0.0000

Data Index: 495066 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3109. Min Act: -0.0000

Data Index: 339136 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1622816 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3094. Min Act: -0.0000

Data Index: 202049 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1564296 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3323. Min Act: -0.0000

Data Index: 381759 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.2777. Min Act: -0.0000

Data Index: 949462 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1178473 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1234547 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.2948. Min Act: -0.0000

Data Index: 764703 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.2899. Min Act: -0.0000

Data Index: 527256 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.4230. Min Range: -0.4230

Max Act: 0.3216. Min Act: -0.0000

Data Index: 598779 (The Pile)

Max Activating Token Index: 896