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

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

Neuron 655 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1281833 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2916. Min Act: -0.0000

Data Index: 807230 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2427. Min Act: -0.0000

Data Index: 930010 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2387. Min Act: -0.0000

Data Index: 852936 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2607. Min Act: -0.0000

Data Index: 94209 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2310. Min Act: -0.0000

Data Index: 893635 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2267. Min Act: -0.0001

Data Index: 45591 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2211. Min Act: -0.0001

Data Index: 257546 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2148. Min Act: -0.0001

Data Index: 358236 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2236. Min Act: -0.0001

Data Index: 591647 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2157. Min Act: -0.0001

Data Index: 27780 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2083. Min Act: -0.0001

Data Index: 679265 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2102. Min Act: -0.0000

Data Index: 270821 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2123. Min Act: -0.0001

Data Index: 895314 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2183. Min Act: -0.0001

Data Index: 95934 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.1936. Min Act: -0.0000

Data Index: 213993 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2165. Min Act: -0.0001

Data Index: 543333 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2026. Min Act: -0.0000

Data Index: 626846 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.1984. Min Act: -0.0000

Data Index: 45566 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2043. Min Act: -0.0000

Data Index: 498571 (C4 (Web Text))

Max Activating Token Index: 228