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

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

Neuron 1790 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: 0.2774. Min Range: -0.2774

Max Act: 0.2774. Min Act: 0.0000

Data Index: 1174847 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2534. Min Act: -0.0001

Data Index: 1178230 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2573. Min Act: -0.0000

Data Index: 371681 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1083847 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2411. Min Act: -0.0000

Data Index: 674160 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2360. Min Act: -0.0001

Data Index: 534590 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2221. Min Act: -0.0000

Data Index: 700824 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2340. Min Act: -0.0000

Data Index: 117478 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2178. Min Act: -0.0000

Data Index: 274195 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1236202 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2200. Min Act: 0.0002

Data Index: 350004 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2273. Min Act: -0.0000

Data Index: 877739 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2108. Min Act: -0.0000

Data Index: 625300 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2108. Min Act: -0.0000

Data Index: 521658 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1221357 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2054. Min Act: -0.0000

Data Index: 221075 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2100. Min Act: -0.0000

Data Index: 126183 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2089. Min Act: -0.0000

Data Index: 313998 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2006. Min Act: -0.0001

Data Index: 586295 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.2774. Min Range: -0.2774

Max Act: 0.2073. Min Act: -0.0000

Data Index: 463242 (C4 (Web Text))

Max Activating Token Index: 720