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

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

Neuron 2917 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1373462 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0191. Min Act: -0.0003

Data Index: 926461 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0174. Min Act: -0.0002

Data Index: 907784 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1014826 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1420167 (Python Code)

Max Activating Token Index: 969

Text #5

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1538642 (Python Code)

Max Activating Token Index: 233

Text #6

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0162. Min Act: -0.0002

Data Index: 449038 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1391960 (Python Code)

Max Activating Token Index: 681

Text #8

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0165. Min Act: -0.0002

Data Index: 733046 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0167. Min Act: -0.0002

Data Index: 868353 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1040808 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1378067 (Python Code)

Max Activating Token Index: 885

Text #12

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1541433 (Python Code)

Max Activating Token Index: 981

Text #13

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0150. Min Act: -0.0002

Data Index: 201621 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1622322 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1079667 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0171. Min Act: -0.0002

Data Index: 712 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0161. Min Act: -0.0002

Data Index: 247836 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1455903 (Python Code)

Max Activating Token Index: 312

Text #19

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0161. Min Act: -0.0002

Data Index: 799293 (C4 (Web Text))

Max Activating Token Index: 978