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

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

Neuron 4947 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: 0.5524. Min Range: -0.5524

Max Act: 0.5524. Min Act: 0.0000

Data Index: 207019 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3648. Min Act: -0.0000

Data Index: 573758 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1058607 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.4064. Min Act: -0.0000

Data Index: 962100 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3283. Min Act: -0.0000

Data Index: 532337 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3390. Min Act: -0.0000

Data Index: 206159 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.2893. Min Act: -0.0000

Data Index: 329041 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1073935 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3301. Min Act: -0.0000

Data Index: 133135 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3159. Min Act: -0.0000

Data Index: 464449 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3003. Min Act: -0.0000

Data Index: 676502 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3253. Min Act: -0.0000

Data Index: 551657 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1329955 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3258. Min Act: -0.0000

Data Index: 141150 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1271317 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3114. Min Act: -0.0000

Data Index: 143502 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.2693. Min Act: -0.0000

Data Index: 111906 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.3577. Min Act: 0.0000

Data Index: 801711 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1326104 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.5524. Min Range: -0.5524

Max Act: 0.2679. Min Act: -0.0000

Data Index: 51339 (C4 (Web Text))

Max Activating Token Index: 684