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

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

Neuron 3487 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: 0.3232. Min Range: -0.3232

Max Act: 0.3227. Min Act: -0.0000

Data Index: 125074 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.3022. Min Act: -0.0000

Data Index: 402852 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1254659 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1080343 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1020735 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1255743 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2888. Min Act: -0.0000

Data Index: 677454 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2912. Min Act: -0.0000

Data Index: 512117 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1416259 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2811. Min Act: -0.0000

Data Index: 105607 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1222839 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2615. Min Act: -0.0000

Data Index: 582685 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2708. Min Act: -0.0000

Data Index: 317842 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2594. Min Act: -0.0000

Data Index: 16758 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2574. Min Act: -0.0000

Data Index: 369238 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2649. Min Act: -0.0000

Data Index: 625465 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2661. Min Act: -0.0000

Data Index: 782279 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1354190 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2521. Min Act: -0.0000

Data Index: 214802 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.3232. Min Range: -0.3232

Max Act: 0.2586. Min Act: -0.0000

Data Index: 307813 (C4 (Web Text))

Max Activating Token Index: 415