Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2986 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.7293. Min Range: -4.7293

Max Act: 4.2781. Min Act: -0.0001

Data Index: 903486 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 4.7293. Min Range: -4.7293

Max Act: 4.7293. Min Act: -0.0001

Data Index: 1160086 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 4.7293. Min Range: -4.7293

Max Act: 4.1204. Min Act: -0.0001

Data Index: 1227651 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 4.7293. Min Range: -4.7293

Max Act: 4.4380. Min Act: -0.0001

Data Index: 610624 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.6953. Min Act: -0.0001

Data Index: 340592 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 4.7293. Min Range: -4.7293

Max Act: 4.0147. Min Act: -0.0001

Data Index: 169617 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 4.7293. Min Range: -4.7293

Max Act: 4.0013. Min Act: -0.0001

Data Index: 284655 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.7887. Min Act: -0.0001

Data Index: 522828 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 4.7293. Min Range: -4.7293

Max Act: 4.1165. Min Act: -0.0001

Data Index: 734764 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.9218. Min Act: -0.0001

Data Index: 571362 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.9240. Min Act: -0.0001

Data Index: 474958 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.7500. Min Act: -0.0001

Data Index: 1080102 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.8902. Min Act: -0.0001

Data Index: 1019245 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.8988. Min Act: -0.0001

Data Index: 1077427 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.7447. Min Act: -0.0001

Data Index: 398856 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.8746. Min Act: -0.0001

Data Index: 348054 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.6489. Min Act: -0.0001

Data Index: 479846 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.9643. Min Act: -0.0001

Data Index: 53998 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.9518. Min Act: -0.0001

Data Index: 853996 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 4.7293. Min Range: -4.7293

Max Act: 3.9476. Min Act: -0.0001

Data Index: 257156 (C4 (Web Text))

Max Activating Token Index: 878