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

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

Neuron 1470 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3206. Min Range: -4.3206

Max Act: 4.2552. Min Act: -0.0000

Data Index: 1284605 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 4.3206. Min Range: -4.3206

Max Act: 4.1593. Min Act: -0.0000

Data Index: 52430 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 4.3206. Min Range: -4.3206

Max Act: 4.3206. Min Act: -0.0000

Data Index: 979901 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.9482. Min Act: -0.0000

Data Index: 90999 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.9434. Min Act: -0.0000

Data Index: 821457 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 4.3206. Min Range: -4.3206

Max Act: 4.1203. Min Act: -0.0000

Data Index: 1009427 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.9355. Min Act: -0.0000

Data Index: 212539 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 4.3206. Min Range: -4.3206

Max Act: 4.1080. Min Act: -0.0000

Data Index: 396343 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.9376. Min Act: -0.0000

Data Index: 331285 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.9194. Min Act: -0.0000

Data Index: 780806 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.8755. Min Act: -0.0000

Data Index: 236069 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.4976. Min Act: -0.0000

Data Index: 1240268 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.8057. Min Act: -0.0000

Data Index: 967191 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.7213. Min Act: -0.0000

Data Index: 123130 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.8804. Min Act: -0.0000

Data Index: 1068376 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.7306. Min Act: -0.0000

Data Index: 2117 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.7504. Min Act: -0.0000

Data Index: 670301 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.5308. Min Act: -0.0000

Data Index: 716108 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.6837. Min Act: -0.0000

Data Index: 800914 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 4.3206. Min Range: -4.3206

Max Act: 3.5408. Min Act: -0.0000

Data Index: 916309 (C4 (Web Text))

Max Activating Token Index: 324