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

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

Neuron 4001 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3477. Min Act: -0.0000

Data Index: 770387 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1344856 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3034. Min Act: -0.0000

Data Index: 30101 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2620. Min Act: -0.0000

Data Index: 86805 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2597. Min Act: -0.0000

Data Index: 558515 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2434. Min Act: -0.0000

Data Index: 514714 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2613. Min Act: -0.0000

Data Index: 955243 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2396. Min Act: -0.0000

Data Index: 225065 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2313. Min Act: -0.0000

Data Index: 582386 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1262428 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2350. Min Act: -0.0000

Data Index: 710449 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2328. Min Act: -0.0000

Data Index: 60077 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2308. Min Act: -0.0000

Data Index: 645699 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1255164 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2472. Min Act: -0.0000

Data Index: 887197 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2453. Min Act: -0.0000

Data Index: 551198 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2215. Min Act: -0.0000

Data Index: 933647 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2406. Min Act: -0.0000

Data Index: 504082 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2275. Min Act: -0.0000

Data Index: 190597 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1036821 (C4 (Web Text))

Max Activating Token Index: 860