Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 974 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2674. Min Act: -0.0006

Data Index: 381430 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2418. Min Act: -0.0006

Data Index: 644528 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2571. Min Act: -0.0006

Data Index: 897674 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2551. Min Act: -0.0006

Data Index: 802400 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2442. Min Act: -0.0006

Data Index: 123006 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2430. Min Act: -0.0006

Data Index: 138814 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2597. Min Act: -0.0006

Data Index: 813463 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2424. Min Act: -0.0006

Data Index: 1014830 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2328. Min Act: -0.0006

Data Index: 484902 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2233. Min Act: -0.0006

Data Index: 1126247 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2235. Min Act: -0.0006

Data Index: 457033 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2887. Min Act: -0.0006

Data Index: 40490 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2481. Min Act: -0.0006

Data Index: 221785 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2381. Min Act: -0.0006

Data Index: 457298 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2052. Min Act: -0.0006

Data Index: 957432 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2358. Min Act: -0.0006

Data Index: 700070 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2347. Min Act: -0.0006

Data Index: 439022 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2167. Min Act: -0.0006

Data Index: 272341 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2409. Min Act: -0.0006

Data Index: 170616 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2398. Min Act: -0.0006

Data Index: 522342 (C4 (Web Text))

Max Activating Token Index: 489