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

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

Neuron 353 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: 0.8842. Min Range: -0.8842

Max Act: 0.8842. Min Act: -0.0000

Data Index: 78728 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.8330. Min Act: -0.0000

Data Index: 389665 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.7910. Min Act: -0.0000

Data Index: 761481 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1147667 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1324784 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.6205. Min Act: -0.0000

Data Index: 547618 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.6255. Min Act: 0.0000

Data Index: 19444 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.6227. Min Act: -0.0000

Data Index: 70767 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.6100. Min Act: -0.0000

Data Index: 889049 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1119425 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.6049. Min Act: 0.0000

Data Index: 1015450 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.6088. Min Act: 0.0000

Data Index: 70066 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.5828. Min Act: 0.0001

Data Index: 1084207 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.6286. Min Act: -0.0000

Data Index: 301174 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.6085. Min Act: 0.0001

Data Index: 1061807 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.5581. Min Act: 0.0001

Data Index: 872153 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.5166. Min Act: 0.0000

Data Index: 23849 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.5129. Min Act: 0.0001

Data Index: 742182 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.5395. Min Act: -0.0000

Data Index: 8448 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.8842. Min Range: -0.8842

Max Act: 0.4989. Min Act: 0.0001

Data Index: 625893 (C4 (Web Text))

Max Activating Token Index: 315