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

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

Neuron 4864 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.5550. Min Act: -0.0000

Data Index: 48669 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.5076. Min Act: -0.0000

Data Index: 303042 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.3606. Min Act: -0.0000

Data Index: 610115 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.3564. Min Act: -0.0000

Data Index: 1065270 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.3820. Min Act: -0.0000

Data Index: 872661 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.3159. Min Act: -0.0000

Data Index: 369006 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2800. Min Act: -0.0000

Data Index: 1154608 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2629. Min Act: -0.0000

Data Index: 1210464 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2925. Min Act: -0.0000

Data Index: 331886 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2571. Min Act: -0.0000

Data Index: 975989 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2352. Min Act: -0.0000

Data Index: 846461 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.3002. Min Act: -0.0000

Data Index: 880717 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2501. Min Act: -0.0000

Data Index: 287409 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1005977 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2091. Min Act: -0.0000

Data Index: 489753 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2358. Min Act: -0.0000

Data Index: 806960 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2376. Min Act: -0.0000

Data Index: 833027 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2190. Min Act: -0.0000

Data Index: 617564 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.1672. Min Act: -0.0000

Data Index: 15598 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 1.5550. Min Range: -1.5550

Max Act: 1.2027. Min Act: -0.0000

Data Index: 258801 (C4 (Web Text))

Max Activating Token Index: 101