Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1767 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0239. Min Act: -0.0005

Data Index: 1411055 (Python Code)

Max Activating Token Index: 150

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0191. Min Act: -0.0004

Data Index: 1594282 (Python Code)

Max Activating Token Index: 392

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0169. Min Act: -0.0004

Data Index: 1446813 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1428317 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0158. Min Act: -0.0005

Data Index: 999662 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0155. Min Act: -0.0005

Data Index: 790951 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1236407 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0151. Min Act: -0.0005

Data Index: 1486426 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0148. Min Act: -0.0006

Data Index: 327759 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0148. Min Act: -0.0004

Data Index: 1538878 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1385440 (Python Code)

Max Activating Token Index: 242

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1345702 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1099187 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1649409 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0144. Min Act: -0.0006

Data Index: 606145 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0144. Min Act: -0.0005

Data Index: 1194035 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0141. Min Act: -0.0005

Data Index: 253573 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0142. Min Act: -0.0006

Data Index: 316561 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0142. Min Act: -0.0006

Data Index: 206478 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1139586 (C4 (Web Text))

Max Activating Token Index: 948