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

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

Neuron 3244 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2895. Min Act: -0.0001

Data Index: 365625 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2676. Min Act: -0.0000

Data Index: 203365 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2649. Min Act: -0.0001

Data Index: 886208 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2835. Min Act: -0.0001

Data Index: 980295 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2490. Min Act: -0.0001

Data Index: 594493 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2534. Min Act: -0.0001

Data Index: 1208737 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2517. Min Act: -0.0001

Data Index: 815823 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1206013 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2485. Min Act: -0.0001

Data Index: 1317084 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2559. Min Act: -0.0001

Data Index: 567397 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2583. Min Act: -0.0000

Data Index: 689593 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2400. Min Act: -0.0001

Data Index: 106132 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2415. Min Act: -0.0000

Data Index: 606206 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2319. Min Act: -0.0001

Data Index: 946185 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2473. Min Act: -0.0001

Data Index: 893707 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2552. Min Act: -0.0001

Data Index: 204097 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2469. Min Act: -0.0001

Data Index: 1016393 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1081163 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2481. Min Act: -0.0001

Data Index: 640383 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2542. Min Act: -0.0000

Data Index: 640123 (C4 (Web Text))

Max Activating Token Index: 234