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

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

Neuron 3326 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: 0.4215. Min Range: -0.4215

Max Act: 0.4215. Min Act: -0.0000

Data Index: 476641 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3866. Min Act: -0.0000

Data Index: 193686 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3942. Min Act: -0.0000

Data Index: 204907 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1058440 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3694. Min Act: -0.0000

Data Index: 451859 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3689. Min Act: -0.0000

Data Index: 891976 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3427. Min Act: -0.0000

Data Index: 243749 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3413. Min Act: -0.0000

Data Index: 371479 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3427. Min Act: -0.0000

Data Index: 591209 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1199249 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3306. Min Act: -0.0000

Data Index: 655188 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3239. Min Act: -0.0000

Data Index: 528923 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3308. Min Act: -0.0000

Data Index: 932692 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3287. Min Act: 0.0000

Data Index: 447894 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3056. Min Act: -0.0000

Data Index: 552219 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3229. Min Act: -0.0000

Data Index: 699567 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3183. Min Act: -0.0000

Data Index: 47329 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3268. Min Act: -0.0000

Data Index: 411518 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3038. Min Act: -0.0000

Data Index: 233967 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.4215. Min Range: -0.4215

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1090745 (C4 (Web Text))

Max Activating Token Index: 438