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

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

Neuron 91 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: 0.0350. Min Range: -0.0350

Max Act: 0.0350. Min Act: -0.0003

Data Index: 631327 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1128257 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0306. Min Act: -0.0003

Data Index: 621978 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0303. Min Act: -0.0003

Data Index: 602564 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0333. Min Act: -0.0003

Data Index: 810367 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0333. Min Act: -0.0003

Data Index: 341444 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0314. Min Act: -0.0003

Data Index: 551697 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0346. Min Act: -0.0003

Data Index: 973857 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0318. Min Act: -0.0003

Data Index: 352273 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0325. Min Act: -0.0003

Data Index: 402240 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0325. Min Act: -0.0003

Data Index: 793751 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0343. Min Act: -0.0003

Data Index: 523023 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1124440 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0302. Min Act: -0.0003

Data Index: 501920 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1213822 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0310. Min Act: -0.0003

Data Index: 809673 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0280. Min Act: -0.0003

Data Index: 883782 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0305. Min Act: -0.0003

Data Index: 486765 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0275. Min Act: -0.0003

Data Index: 768017 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0350. Min Range: -0.0350

Max Act: 0.0322. Min Act: -0.0003

Data Index: 665549 (C4 (Web Text))

Max Activating Token Index: 949