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

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

Neuron 5193 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.5224. Min Act: -0.0000

Data Index: 925600 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4584. Min Act: -0.0000

Data Index: 411419 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4275. Min Act: -0.0000

Data Index: 463370 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4299. Min Act: -0.0000

Data Index: 850666 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4041. Min Act: -0.0000

Data Index: 480719 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3745. Min Act: -0.0000

Data Index: 794697 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3887. Min Act: -0.0000

Data Index: 448695 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1085297 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3689. Min Act: -0.0000

Data Index: 205480 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3457. Min Act: -0.0000

Data Index: 16840 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3412. Min Act: -0.0000

Data Index: 896889 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3483. Min Act: -0.0000

Data Index: 239971 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3535. Min Act: -0.0000

Data Index: 986603 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3400. Min Act: -0.0000

Data Index: 466465 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3573. Min Act: -0.0000

Data Index: 140393 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3394. Min Act: -0.0000

Data Index: 534263 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3641. Min Act: -0.0000

Data Index: 452449 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2994. Min Act: -0.0000

Data Index: 626631 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3181. Min Act: -0.0000

Data Index: 790118 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3181. Min Act: -0.0000

Data Index: 724826 (C4 (Web Text))

Max Activating Token Index: 404