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

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

Neuron 3583 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.3513. Min Act: -0.0001

Data Index: 701338 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1029286 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2912. Min Act: -0.0000

Data Index: 248043 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1208221 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2680. Min Act: -0.0000

Data Index: 545716 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1139305 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2527. Min Act: -0.0000

Data Index: 737353 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2621. Min Act: -0.0001

Data Index: 788767 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2557. Min Act: -0.0000

Data Index: 395966 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2502. Min Act: -0.0000

Data Index: 646219 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2371. Min Act: -0.0001

Data Index: 455191 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2358. Min Act: -0.0000

Data Index: 153350 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2335. Min Act: -0.0000

Data Index: 331152 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2418. Min Act: -0.0000

Data Index: 216592 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2303. Min Act: -0.0001

Data Index: 1241209 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1023212 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1262677 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2232. Min Act: -0.0000

Data Index: 32193 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2216. Min Act: -0.0000

Data Index: 44216 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.3513. Min Range: -0.3513

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1349615 (C4 (Web Text))

Max Activating Token Index: 240