Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 769 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1028577 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1274. Min Act: -0.0002

Data Index: 114270 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1262. Min Act: -0.0002

Data Index: 24506 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1637609 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1261. Min Act: -0.0002

Data Index: 79369 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1095. Min Act: -0.0002

Data Index: 585113 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1351. Min Act: -0.0002

Data Index: 112730 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1165. Min Act: -0.0002

Data Index: 266298 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1242. Min Act: -0.0002

Data Index: 827079 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1297573 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1297476 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1217. Min Act: -0.0002

Data Index: 788092 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1255. Min Act: -0.0002

Data Index: 331107 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1090. Min Act: -0.0002

Data Index: 631353 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1120. Min Act: -0.0002

Data Index: 262959 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1267977 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1154. Min Act: -0.0002

Data Index: 558441 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1235. Min Act: -0.0002

Data Index: 805249 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1103. Min Act: -0.0001

Data Index: 1499807 (Python Code)

Max Activating Token Index: 428

Text #19

Max Range: 0.1351. Min Range: -0.1351

Max Act: 0.1044. Min Act: -0.0002

Data Index: 6789 (C4 (Web Text))

Max Activating Token Index: 529