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

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

Neuron 3950 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.3262. Min Act: -0.0001

Data Index: 126059 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.3203. Min Act: -0.0001

Data Index: 174202 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.3022. Min Act: -0.0001

Data Index: 118551 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1046947 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1228392 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2957. Min Act: -0.0001

Data Index: 932317 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.3010. Min Act: -0.0001

Data Index: 342419 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.3156. Min Act: -0.0001

Data Index: 58364 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2887. Min Act: -0.0001

Data Index: 59697 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2761. Min Act: -0.0001

Data Index: 713605 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2851. Min Act: -0.0001

Data Index: 60051 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1083660 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1134125 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2443. Min Act: -0.0001

Data Index: 146108 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2712. Min Act: -0.0001

Data Index: 348197 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2785. Min Act: -0.0001

Data Index: 192203 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2796. Min Act: -0.0001

Data Index: 1257330 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2753. Min Act: -0.0001

Data Index: 523376 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2761. Min Act: -0.0001

Data Index: 1275377 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.3262. Min Range: -0.3262

Max Act: 0.2849. Min Act: -0.0001

Data Index: 1128628 (C4 (Web Text))

Max Activating Token Index: 166