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

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

Neuron 3355 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.7085. Min Act: -0.0000

Data Index: 301737 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.5119. Min Act: -0.0000

Data Index: 22891 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.6506. Min Act: -0.0000

Data Index: 356483 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.0805. Min Act: -0.0000

Data Index: 1063464 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.3339. Min Act: -0.0000

Data Index: 538948 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.1714. Min Act: -0.0000

Data Index: 1217078 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.1594. Min Act: -0.0000

Data Index: 136717 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 2.7085. Min Range: -2.7085

Max Act: 2.0399. Min Act: -0.0000

Data Index: 744410 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.9337. Min Act: -0.0000

Data Index: 547597 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.9953. Min Act: -0.0000

Data Index: 398784 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.9343. Min Act: -0.0000

Data Index: 234125 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.7916. Min Act: -0.0000

Data Index: 556846 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.9871. Min Act: -0.0000

Data Index: 671743 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.8261. Min Act: -0.0000

Data Index: 342542 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.9187. Min Act: -0.0000

Data Index: 574830 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.8238. Min Act: -0.0000

Data Index: 1250957 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.9692. Min Act: -0.0000

Data Index: 379971 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.7127. Min Act: -0.0000

Data Index: 26984 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.6698. Min Act: -0.0000

Data Index: 218651 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 2.7085. Min Range: -2.7085

Max Act: 1.7314. Min Act: -0.0000

Data Index: 995383 (C4 (Web Text))

Max Activating Token Index: 731