Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 652 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1440. Min Act: -0.0003

Data Index: 127513 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1345. Min Act: -0.0003

Data Index: 90598 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1310. Min Act: -0.0003

Data Index: 708741 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1321. Min Act: -0.0003

Data Index: 497662 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1313. Min Act: -0.0003

Data Index: 1147607 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1254. Min Act: -0.0003

Data Index: 132744 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1220. Min Act: -0.0003

Data Index: 247818 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1092. Min Act: -0.0003

Data Index: 34413 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1091. Min Act: -0.0003

Data Index: 307298 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1161. Min Act: -0.0003

Data Index: 1268201 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1128. Min Act: -0.0003

Data Index: 1050866 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1075. Min Act: -0.0003

Data Index: 750926 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1350. Min Act: -0.0003

Data Index: 96597 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1105. Min Act: -0.0003

Data Index: 125288 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1212. Min Act: -0.0003

Data Index: 508260 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1085. Min Act: -0.0003

Data Index: 306043 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1167. Min Act: -0.0003

Data Index: 914496 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1244. Min Act: -0.0003

Data Index: 168467 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1177. Min Act: -0.0003

Data Index: 202938 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1059. Min Act: -0.0003

Data Index: 243366 (C4 (Web Text))

Max Activating Token Index: 295