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

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

Neuron 1415 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0354. Min Act: -0.0003

Data Index: 323184 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1479748 (Python Code)

Max Activating Token Index: 909

Text #2

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0347. Min Act: -0.0003

Data Index: 116607 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0309. Min Act: -0.0003

Data Index: 912549 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1378226 (Python Code)

Max Activating Token Index: 31

Text #5

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1569396 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0310. Min Act: -0.0003

Data Index: 88498 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1258761 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0280. Min Act: -0.0003

Data Index: 539647 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0233. Min Act: -0.0003

Data Index: 797857 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1591824 (Python Code)

Max Activating Token Index: 580

Text #11

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1619696 (Python Code)

Max Activating Token Index: 897

Text #12

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1502050 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1032397 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1412322 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1373804 (Python Code)

Max Activating Token Index: 558

Text #16

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0277. Min Act: -0.0003

Data Index: 175994 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1635304 (Python Code)

Max Activating Token Index: 447

Text #18

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0347. Min Act: -0.0004

Data Index: 1456636 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1567943 (Python Code)

Max Activating Token Index: 601