Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4354 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2398. Min Act: -0.0001

Data Index: 141303 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2250. Min Act: -0.0001

Data Index: 979445 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2226. Min Act: -0.0001

Data Index: 474510 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1254845 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2208. Min Act: -0.0001

Data Index: 1202376 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1271599 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2199. Min Act: -0.0001

Data Index: 401828 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2164. Min Act: -0.0002

Data Index: 880364 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2181. Min Act: -0.0001

Data Index: 3353 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2177. Min Act: -0.0001

Data Index: 912771 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2178. Min Act: -0.0001

Data Index: 215522 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2182. Min Act: -0.0001

Data Index: 521070 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2186. Min Act: -0.0001

Data Index: 162635 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2186. Min Act: -0.0001

Data Index: 238586 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2196. Min Act: -0.0001

Data Index: 1180310 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1089486 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1195060 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2141. Min Act: -0.0001

Data Index: 25628 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2139. Min Act: -0.0001

Data Index: 4218 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2144. Min Act: -0.0001

Data Index: 128716 (C4 (Web Text))

Max Activating Token Index: 845