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

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

Neuron 4420 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1391. Min Act: -0.0001

Data Index: 78096 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1392. Min Act: -0.0001

Data Index: 363345 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1103441 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1383. Min Act: -0.0001

Data Index: 897197 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1299. Min Act: -0.0001

Data Index: 967378 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1323. Min Act: -0.0001

Data Index: 272202 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1257. Min Act: -0.0001

Data Index: 785101 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1258. Min Act: -0.0001

Data Index: 380530 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1229. Min Act: -0.0001

Data Index: 149252 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1198. Min Act: -0.0001

Data Index: 646739 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1211. Min Act: -0.0001

Data Index: 97339 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1217. Min Act: -0.0001

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1157. Min Act: -0.0001

Data Index: 390762 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1154. Min Act: -0.0001

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1307817 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1016287 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1166. Min Act: -0.0001

Data Index: 143642 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1305917 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1158. Min Act: -0.0001

Data Index: 452876 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1136. Min Act: -0.0001

Data Index: 860313 (C4 (Web Text))

Max Activating Token Index: 864