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

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

Neuron 629 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.3524. Min Act: -0.0002

Data Index: 109436 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.3157. Min Act: -0.0002

Data Index: 1150337 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.3157. Min Act: -0.0002

Data Index: 1296066 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2762. Min Act: -0.0002

Data Index: 1014854 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.3086. Min Act: -0.0002

Data Index: 405370 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2776. Min Act: -0.0002

Data Index: 29784 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2393. Min Act: -0.0003

Data Index: 219607 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2496. Min Act: -0.0002

Data Index: 502079 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2313. Min Act: -0.0002

Data Index: 89391 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2562. Min Act: -0.0002

Data Index: 503942 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2239. Min Act: -0.0002

Data Index: 345918 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2277. Min Act: -0.0002

Data Index: 146164 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2480. Min Act: -0.0002

Data Index: 130623 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2291. Min Act: -0.0002

Data Index: 853763 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2523. Min Act: -0.0002

Data Index: 1032486 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2282. Min Act: -0.0002

Data Index: 1147801 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2209. Min Act: -0.0002

Data Index: 131747 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2490. Min Act: -0.0002

Data Index: 1199621 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2157. Min Act: -0.0002

Data Index: 745216 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.3524. Min Range: -1.3524

Max Act: 1.2033. Min Act: -0.0002

Data Index: 500646 (C4 (Web Text))

Max Activating Token Index: 711