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

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

Neuron 3808 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0185. Min Act: -0.0001

Data Index: 180935 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1587584 (Python Code)

Max Activating Token Index: 277

Text #2

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1535095 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0175. Min Act: -0.0001

Data Index: 595965 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0174. Min Act: -0.0001

Data Index: 7345 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1456187 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0161. Min Act: -0.0001

Data Index: 23393 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1215513 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0155. Min Act: -0.0001

Data Index: 153007 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1058662 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1310606 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1617633 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0153. Min Act: -0.0001

Data Index: 1457134 (Python Code)

Max Activating Token Index: 298

Text #13

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0153. Min Act: -0.0001

Data Index: 949511 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0143. Min Act: -0.0001

Data Index: 771812 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0154. Min Act: -0.0001

Data Index: 1524230 (Python Code)

Max Activating Token Index: 385

Text #16

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0143. Min Act: -0.0001

Data Index: 459218 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0139. Min Act: -0.0001

Data Index: 1237765 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0157. Min Act: -0.0001

Data Index: 988570 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0187. Min Range: -0.0187

Max Act: 0.0148. Min Act: -0.0001

Data Index: 83844 (C4 (Web Text))

Max Activating Token Index: 94