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

Dataset: The Pile

Neuron 2273 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1540342 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1522699 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3475. Min Act: -0.0000

Data Index: 935182 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1377929 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1008012 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4220. Min Act: -0.0000

Data Index: 431548 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1455399 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1981858 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1965739 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3432. Min Act: -0.0000

Data Index: 632932 (The Pile)

Max Activating Token Index: 929

Text #10

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1855494 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3258. Min Act: -0.0000

Data Index: 581182 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3337. Min Act: -0.0000

Data Index: 727014 (The Pile)

Max Activating Token Index: 513

Text #13

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1667570 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3030. Min Act: -0.0000

Data Index: 279276 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.2770. Min Act: -0.0000

Data Index: 225336 (The Pile)

Max Activating Token Index: 684

Text #16

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3201. Min Act: -0.0000

Data Index: 615020 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.2828. Min Act: -0.0000

Data Index: 733979 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1196157 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3050. Min Act: -0.0000

Data Index: 316102 (The Pile)

Max Activating Token Index: 894