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

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

Neuron 1856 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3525. Min Act: -0.0000

Data Index: 489015 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1170656 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3744. Min Act: -0.0000

Data Index: 315364 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1186907 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1115054 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3257. Min Act: -0.0000

Data Index: 552787 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1246244 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3056. Min Act: -0.0000

Data Index: 641175 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1272968 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3149. Min Act: -0.0000

Data Index: 810837 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3000. Min Act: -0.0000

Data Index: 734723 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3122. Min Act: -0.0000

Data Index: 71389 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.3040. Min Act: -0.0000

Data Index: 695898 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2709. Min Act: -0.0000

Data Index: 698662 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2762. Min Act: -0.0000

Data Index: 917804 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2654. Min Act: -0.0000

Data Index: 814020 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2713. Min Act: -0.0000

Data Index: 555681 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2444. Min Act: -0.0000

Data Index: 222051 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1027785 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.3744. Min Range: -0.3744

Max Act: 0.2584. Min Act: -0.0000

Data Index: 755282 (C4 (Web Text))

Max Activating Token Index: 379