Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2585 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5877. Min Range: -2.5877

Max Act: 2.5877. Min Act: -0.0000

Data Index: 551985 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 2.5877. Min Range: -2.5877

Max Act: 2.3838. Min Act: -0.0000

Data Index: 480286 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 2.5877. Min Range: -2.5877

Max Act: 2.1204. Min Act: -0.0000

Data Index: 353630 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 2.5877. Min Range: -2.5877

Max Act: 2.2634. Min Act: -0.0000

Data Index: 1344096 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.8343. Min Act: -0.0000

Data Index: 1016110 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.8995. Min Act: -0.0000

Data Index: 311855 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 2.5877. Min Range: -2.5877

Max Act: 2.1247. Min Act: -0.0000

Data Index: 9123 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 2.5877. Min Range: -2.5877

Max Act: 2.0472. Min Act: -0.0000

Data Index: 1051123 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.9347. Min Act: -0.0000

Data Index: 1292091 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.9224. Min Act: -0.0000

Data Index: 352388 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.8014. Min Act: -0.0000

Data Index: 295720 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.8742. Min Act: -0.0000

Data Index: 291092 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.9545. Min Act: -0.0000

Data Index: 1185774 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.5526. Min Act: -0.0000

Data Index: 465589 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.9651. Min Act: -0.0000

Data Index: 950053 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.7195. Min Act: -0.0000

Data Index: 1288792 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.9915. Min Act: -0.0000

Data Index: 729852 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.4961. Min Act: -0.0000

Data Index: 328813 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.6893. Min Act: -0.0000

Data Index: 1242049 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 2.5877. Min Range: -2.5877

Max Act: 1.8472. Min Act: -0.0000

Data Index: 678850 (C4 (Web Text))

Max Activating Token Index: 193