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

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

Neuron 5117 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1085514 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.8578. Min Act: -0.0000

Data Index: 859415 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1218417 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.6832. Min Act: -0.0000

Data Index: 170470 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5703. Min Act: -0.0000

Data Index: 357281 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1130783 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.6049. Min Act: -0.0000

Data Index: 51456 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.6241. Min Act: -0.0000

Data Index: 686755 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5661. Min Act: -0.0000

Data Index: 329997 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5782. Min Act: -0.0000

Data Index: 722728 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5507. Min Act: -0.0000

Data Index: 890273 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1282218 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5485. Min Act: -0.0000

Data Index: 818483 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1067496 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5380. Min Act: -0.0000

Data Index: 815632 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1185005 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1203721 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5152. Min Act: -0.0000

Data Index: 704955 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.4933. Min Act: -0.0000

Data Index: 97018 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.8578. Min Range: -0.8578

Max Act: 0.5237. Min Act: -0.0000

Data Index: 660053 (C4 (Web Text))

Max Activating Token Index: 593