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

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

Neuron 3849 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.3798. Min Act: -0.0000

Data Index: 1288298 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0411. Min Act: 0.0000

Data Index: 1335028 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1059. Min Act: -0.0000

Data Index: 988972 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0297. Min Act: -0.0000

Data Index: 738007 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1029686 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0260. Min Act: -0.0000

Data Index: 324821 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0056. Min Act: -0.0000

Data Index: 748111 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0058. Min Act: -0.0000

Data Index: 383068 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8736. Min Act: -0.0000

Data Index: 669004 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0158. Min Act: -0.0000

Data Index: 182435 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1327663 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9417. Min Act: -0.0000

Data Index: 311660 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1303122 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9303. Min Act: -0.0000

Data Index: 240358 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1209202 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8716. Min Act: -0.0000

Data Index: 298413 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9114. Min Act: -0.0000

Data Index: 320013 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8785. Min Act: -0.0000

Data Index: 374529 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8215. Min Act: -0.0000

Data Index: 394167 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8429. Min Act: -0.0000

Data Index: 665512 (C4 (Web Text))

Max Activating Token Index: 572