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

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

Neuron 3405 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.4415. Min Act: -0.0000

Data Index: 929643 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.4457. Min Act: -0.0000

Data Index: 765139 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1003825 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3674. Min Act: -0.0000

Data Index: 615552 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1250065 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3340. Min Act: -0.0000

Data Index: 912869 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3307. Min Act: -0.0000

Data Index: 286615 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3253. Min Act: -0.0000

Data Index: 935048 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3380. Min Act: -0.0000

Data Index: 878623 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3136. Min Act: -0.0000

Data Index: 256349 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3223. Min Act: -0.0000

Data Index: 648042 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3166. Min Act: -0.0000

Data Index: 929968 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2896. Min Act: -0.0000

Data Index: 91777 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1081962 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3182. Min Act: -0.0000

Data Index: 953983 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2937. Min Act: -0.0000

Data Index: 557293 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3060. Min Act: -0.0000

Data Index: 342095 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.3108. Min Act: -0.0000

Data Index: 682787 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2888. Min Act: -0.0000

Data Index: 277782 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.4457. Min Range: -0.4457

Max Act: 0.2964. Min Act: -0.0000

Data Index: 347708 (C4 (Web Text))

Max Activating Token Index: 609