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

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

Neuron 4717 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: 0.5008. Min Range: -0.5008

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1041707 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4958. Min Act: -0.0000

Data Index: 892275 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4738. Min Act: -0.0000

Data Index: 149371 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3228. Min Act: -0.0000

Data Index: 17440 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2937. Min Act: -0.0000

Data Index: 529355 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1040662 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3010. Min Act: -0.0000

Data Index: 312589 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2855. Min Act: -0.0000

Data Index: 1015037 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3046. Min Act: -0.0000

Data Index: 201609 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1245448 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2780. Min Act: -0.0000

Data Index: 565678 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1272543 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2676. Min Act: -0.0000

Data Index: 598837 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2793. Min Act: -0.0000

Data Index: 669199 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2773. Min Act: -0.0000

Data Index: 14902 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1055456 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2712. Min Act: -0.0000

Data Index: 514191 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1282389 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1101062 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1026811 (C4 (Web Text))

Max Activating Token Index: 418