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

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

Neuron 3921 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1212873 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3465. Min Act: -0.0000

Data Index: 411874 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1179908 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3488. Min Act: -0.0000

Data Index: 128018 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3307. Min Act: -0.0000

Data Index: 229861 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3325. Min Act: -0.0000

Data Index: 951768 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1230611 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3385. Min Act: -0.0000

Data Index: 181197 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1209260 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3237. Min Act: -0.0000

Data Index: 883351 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3247. Min Act: -0.0000

Data Index: 349250 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1148193 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.2943. Min Act: -0.0000

Data Index: 205073 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1354802 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.2948. Min Act: -0.0000

Data Index: 646907 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.2868. Min Act: -0.0000

Data Index: 506425 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.2808. Min Act: -0.0000

Data Index: 259218 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.2671. Min Act: -0.0000

Data Index: 22782 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1235058 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.4386. Min Range: -0.4386

Max Act: 0.2720. Min Act: -0.0000

Data Index: 854335 (C4 (Web Text))

Max Activating Token Index: 152