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

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

Neuron 3138 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0397. Min Act: -0.0001

Data Index: 1168519 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1565078 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0345. Min Act: -0.0001

Data Index: 41967 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1238262 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1199242 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0317. Min Act: -0.0001

Data Index: 363289 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0327. Min Act: -0.0001

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0354. Min Act: -0.0001

Data Index: 496039 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0313. Min Act: -0.0001

Data Index: 395083 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0367. Min Act: -0.0001

Data Index: 995156 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0335. Min Act: -0.0001

Data Index: 672395 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0321. Min Act: -0.0001

Data Index: 99850 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1097560 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0315. Min Act: -0.0001

Data Index: 609319 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1130869 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1305869 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0259. Min Act: -0.0001

Data Index: 890551 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0310. Min Act: -0.0001

Data Index: 796148 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0309. Min Act: -0.0001

Data Index: 759742 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1015157 (C4 (Web Text))

Max Activating Token Index: 396