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

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

Neuron 103 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: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0003

Data Index: 604547 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1285478 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0346. Min Act: -0.0003

Data Index: 725231 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1305400 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1041508 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0318. Min Act: -0.0003

Data Index: 912593 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1234442 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0301. Min Act: -0.0003

Data Index: 390566 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1133831 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1031028 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0304. Min Act: -0.0003

Data Index: 331843 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0271. Min Act: -0.0003

Data Index: 940679 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0312. Min Act: -0.0003

Data Index: 294162 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0294. Min Act: -0.0003

Data Index: 446495 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0240. Min Act: -0.0003

Data Index: 627910 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0315. Min Act: -0.0003

Data Index: 44759 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0262. Min Act: -0.0003

Data Index: 542804 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0255. Min Act: -0.0003

Data Index: 840572 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1236 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0282. Min Act: -0.0003

Data Index: 593807 (C4 (Web Text))

Max Activating Token Index: 120