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

Dataset: The Pile

Neuron 4083 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1725985 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.7234. Min Act: -0.0000

Data Index: 951290 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6507. Min Act: -0.0000

Data Index: 250843 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6892. Min Act: -0.0000

Data Index: 864744 (The Pile)

Max Activating Token Index: 84

Text #4

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1387105 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6491. Min Act: -0.0000

Data Index: 683394 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1730425 (The Pile)

Max Activating Token Index: 358

Text #7

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6217. Min Act: -0.0000

Data Index: 718563 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6224. Min Act: -0.0000

Data Index: 119906 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1095704 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1362500 (The Pile)

Max Activating Token Index: 63

Text #11

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1015839 (The Pile)

Max Activating Token Index: 427

Text #12

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6272. Min Act: -0.0000

Data Index: 795045 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1886271 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1431781 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6081. Min Act: -0.0000

Data Index: 381928 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1980009 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1120843 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1990437 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1315784 (The Pile)

Max Activating Token Index: 326