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

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

Neuron 939 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0201. Min Act: -0.0006

Data Index: 237317 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0187. Min Act: -0.0006

Data Index: 448823 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0190. Min Act: -0.0006

Data Index: 717680 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0182. Min Act: -0.0006

Data Index: 72131 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0181. Min Act: -0.0006

Data Index: 346005 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1139035 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0184. Min Act: -0.0005

Data Index: 170606 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0170. Min Act: -0.0006

Data Index: 109364 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0184. Min Act: -0.0006

Data Index: 667965 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0175. Min Act: -0.0006

Data Index: 894363 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0170. Min Act: -0.0006

Data Index: 203258 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1174896 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1050273 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0169. Min Act: -0.0005

Data Index: 990203 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0171. Min Act: -0.0006

Data Index: 975786 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1023045 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0168. Min Act: -0.0006

Data Index: 219203 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1079939 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1078056 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0167. Min Act: -0.0006

Data Index: 349193 (C4 (Web Text))

Max Activating Token Index: 278