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

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

Neuron 3704 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: 0.1440. Min Range: -0.1440

Max Act: 0.1159. Min Act: -0.0002

Data Index: 407527 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1369. Min Act: -0.0002

Data Index: 890008 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1282185 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1321. Min Act: -0.0002

Data Index: 335726 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1319. Min Act: -0.0002

Data Index: 323117 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1331284 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1166. Min Act: -0.0002

Data Index: 827873 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1072. Min Act: -0.0002

Data Index: 411922 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1191. Min Act: -0.0002

Data Index: 1136936 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1270. Min Act: -0.0002

Data Index: 428327 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1271. Min Act: -0.0002

Data Index: 764037 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1225. Min Act: -0.0002

Data Index: 632815 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1275. Min Act: -0.0002

Data Index: 380821 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1306419 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1181. Min Act: -0.0002

Data Index: 231252 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1309. Min Act: -0.0002

Data Index: 315058 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1130. Min Act: -0.0002

Data Index: 1333968 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1440. Min Act: -0.0002

Data Index: 1241588 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1235. Min Act: -0.0002

Data Index: 1005194 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1021. Min Act: -0.0002

Data Index: 653080 (C4 (Web Text))

Max Activating Token Index: 192