Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1663 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.5657. Min Act: -0.0000

Data Index: 28490 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4926. Min Act: -0.0000

Data Index: 13761 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.5306. Min Act: -0.0000

Data Index: 59359 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4577. Min Act: -0.0000

Data Index: 107902 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4311. Min Act: -0.0000

Data Index: 264879 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4791. Min Act: -0.0001

Data Index: 867385 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1124141 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4383. Min Act: -0.0000

Data Index: 191172 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4916. Min Act: -0.0000

Data Index: 698676 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4404. Min Act: -0.0000

Data Index: 888308 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4323. Min Act: -0.0000

Data Index: 133043 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4325. Min Act: -0.0000

Data Index: 15678 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1069493 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4037. Min Act: -0.0000

Data Index: 585718 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1003577 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4170. Min Act: -0.0000

Data Index: 360613 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.3790. Min Act: -0.0000

Data Index: 513536 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4096. Min Act: -0.0000

Data Index: 836554 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4569. Min Act: -0.0000

Data Index: 980096 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.5657. Min Range: -0.5657

Max Act: 0.4331. Min Act: -0.0000

Data Index: 64081 (C4 (Web Text))

Max Activating Token Index: 98