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

Dataset: The Pile

Neuron 3155 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.7278. Min Act: 0.0000

Data Index: 796231 (The Pile)

Max Activating Token Index: 409

Text #1

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.4923. Min Act: -0.0000

Data Index: 47261 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.5494. Min Act: -0.0000

Data Index: 489849 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.4709. Min Act: -0.0000

Data Index: 8966 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.2474. Min Act: -0.0000

Data Index: 539934 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.3410. Min Act: -0.0000

Data Index: 285679 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.4403. Min Act: -0.0000

Data Index: 1026287 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 3.7278. Min Range: -3.7278

Max Act: 2.8911. Min Act: -0.0000

Data Index: 1104380 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.3082. Min Act: -0.0000

Data Index: 1081327 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.2654. Min Act: -0.0000

Data Index: 936803 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 3.7278. Min Range: -3.7278

Max Act: 2.9785. Min Act: -0.0000

Data Index: 1749538 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.0670. Min Act: -0.0000

Data Index: 1957040 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.2079. Min Act: -0.0000

Data Index: 1319700 (The Pile)

Max Activating Token Index: 128

Text #13

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.0568. Min Act: -0.0000

Data Index: 891435 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 3.7278. Min Range: -3.7278

Max Act: 2.8309. Min Act: -0.0000

Data Index: 248255 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 3.7278. Min Range: -3.7278

Max Act: 2.9587. Min Act: -0.0000

Data Index: 231792 (The Pile)

Max Activating Token Index: 808

Text #16

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.2053. Min Act: -0.0000

Data Index: 802241 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 3.7278. Min Range: -3.7278

Max Act: 3.0857. Min Act: -0.0000

Data Index: 1178181 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 3.7278. Min Range: -3.7278

Max Act: 2.7813. Min Act: -0.0000

Data Index: 1892660 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 3.7278. Min Range: -3.7278

Max Act: 2.7344. Min Act: -0.0000

Data Index: 1223113 (The Pile)

Max Activating Token Index: 612