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

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

Neuron 5678 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.8165. Min Act: -0.0000

Data Index: 891898 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1027877 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6830. Min Act: -0.0000

Data Index: 74744 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6103. Min Act: -0.0000

Data Index: 831936 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.6522. Min Act: -0.0000

Data Index: 922450 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.4778. Min Act: -0.0000

Data Index: 442228 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.5084. Min Act: -0.0000

Data Index: 862899 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.4826. Min Act: -0.0000

Data Index: 131374 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1209848 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.4644. Min Act: -0.0000

Data Index: 365362 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.4239. Min Act: -0.0000

Data Index: 246558 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.4267. Min Act: -0.0000

Data Index: 29502 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.4481. Min Act: -0.0000

Data Index: 505314 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.3963. Min Act: -0.0000

Data Index: 474430 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1019693 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1034242 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.3882. Min Act: 0.0000

Data Index: 1261347 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1319254 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.3780. Min Act: -0.0000

Data Index: 525614 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.8165. Min Range: -0.8165

Max Act: 0.3867. Min Act: -0.0000

Data Index: 51759 (C4 (Web Text))

Max Activating Token Index: 365