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

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

Neuron 1028 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3627. Min Act: -0.0000

Data Index: 225269 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3760. Min Act: 0.0001

Data Index: 563842 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3309. Min Act: -0.0000

Data Index: 503391 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3372. Min Act: 0.0000

Data Index: 757883 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1132263 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3467. Min Act: -0.0000

Data Index: 775708 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3343. Min Act: 0.0000

Data Index: 1167352 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3230. Min Act: -0.0000

Data Index: 100197 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3326. Min Act: 0.0000

Data Index: 165941 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3159. Min Act: 0.0000

Data Index: 396542 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3170. Min Act: -0.0000

Data Index: 347193 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3010. Min Act: -0.0000

Data Index: 291196 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3079. Min Act: -0.0000

Data Index: 961412 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3067. Min Act: -0.0000

Data Index: 497076 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2953. Min Act: -0.0000

Data Index: 972165 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1295106 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2891. Min Act: 0.0000

Data Index: 1180293 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1209490 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2935. Min Act: -0.0000

Data Index: 325117 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2895. Min Act: -0.0000

Data Index: 818769 (C4 (Web Text))

Max Activating Token Index: 1001