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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2037 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0212. Min Range: -2.0212

Max Act: 2.0212. Min Act: 0.0000

Data Index: 865067 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 2.0212. Min Range: -2.0212

Max Act: 1.3151. Min Act: -0.0000

Data Index: 40399 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 2.0212. Min Range: -2.0212

Max Act: 1.1863. Min Act: 0.0000

Data Index: 207180 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 2.0212. Min Range: -2.0212

Max Act: 1.1218. Min Act: 0.0000

Data Index: 951269 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9710. Min Act: -0.0000

Data Index: 562853 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 2.0212. Min Range: -2.0212

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1173239 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9530. Min Act: -0.0000

Data Index: 289217 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9778. Min Act: 0.0000

Data Index: 548701 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1059862 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9538. Min Act: 0.0000

Data Index: 128470 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1225442 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9719. Min Act: -0.0000

Data Index: 138216 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9325. Min Act: 0.0000

Data Index: 214308 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9283. Min Act: 0.0000

Data Index: 1206194 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9250. Min Act: -0.0000

Data Index: 460128 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.8967. Min Act: -0.0000

Data Index: 849771 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9219. Min Act: -0.0000

Data Index: 489407 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9358. Min Act: -0.0000

Data Index: 537743 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.9379. Min Act: -0.0000

Data Index: 196014 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 2.0212. Min Range: -2.0212

Max Act: 0.8417. Min Act: -0.0000

Data Index: 89447 (C4 (Web Text))

Max Activating Token Index: 194