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

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

Neuron 4537 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1334250 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1120058 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0184. Min Act: -0.0003

Data Index: 853654 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0179. Min Act: -0.0003

Data Index: 566313 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0181. Min Act: -0.0003

Data Index: 889780 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1050173 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0179. Min Act: -0.0003

Data Index: 547009 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0175. Min Act: -0.0003

Data Index: 332423 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0168. Min Act: -0.0003

Data Index: 411667 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0159. Min Act: -0.0003

Data Index: 774392 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0160. Min Act: -0.0003

Data Index: 371825 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0163. Min Act: -0.0003

Data Index: 583617 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0164. Min Act: -0.0003

Data Index: 400553 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0162. Min Act: -0.0003

Data Index: 100147 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0153. Min Act: -0.0003

Data Index: 758188 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1322726 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0155. Min Act: -0.0002

Data Index: 589088 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0154. Min Act: -0.0003

Data Index: 776067 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0150. Min Act: -0.0003

Data Index: 30985 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0162. Min Act: -0.0002

Data Index: 163245 (C4 (Web Text))

Max Activating Token Index: 949