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

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

Neuron 4526 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: 2.2190. Min Range: -2.2190

Max Act: 2.2190. Min Act: -0.0000

Data Index: 18719 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.8631. Min Act: -0.0000

Data Index: 1345445 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.8400. Min Act: -0.0000

Data Index: 348237 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.7193. Min Act: -0.0000

Data Index: 13394 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.8085. Min Act: -0.0000

Data Index: 711710 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.7069. Min Act: 0.0001

Data Index: 346405 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.7079. Min Act: -0.0000

Data Index: 1325232 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1029302 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.6774. Min Act: -0.0000

Data Index: 688231 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.6239. Min Act: -0.0000

Data Index: 438029 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.5456. Min Act: -0.0000

Data Index: 305538 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.5440. Min Act: -0.0000

Data Index: 69221 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.6140. Min Act: -0.0000

Data Index: 832856 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.6105. Min Act: 0.0000

Data Index: 178146 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.5099. Min Act: 0.0000

Data Index: 405825 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.5326. Min Act: -0.0000

Data Index: 1208668 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.4082. Min Act: -0.0000

Data Index: 1248060 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.5760. Min Act: -0.0000

Data Index: 192283 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.4748. Min Act: -0.0000

Data Index: 894525 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 2.2190. Min Range: -2.2190

Max Act: 1.3165. Min Act: -0.0000

Data Index: 702504 (C4 (Web Text))

Max Activating Token Index: 800