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

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

Neuron 4106 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.3076. Min Act: -0.0000

Data Index: 142434 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1208760 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1149365 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1326. Min Act: -0.0000

Data Index: 418044 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1413. Min Act: -0.0000

Data Index: 245521 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1322. Min Act: -0.0000

Data Index: 1012829 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1323. Min Act: -0.0000

Data Index: 454443 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 1.3076. Min Range: -1.3076

Max Act: 0.9790. Min Act: -0.0000

Data Index: 140822 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0877. Min Act: -0.0000

Data Index: 101768 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1745. Min Act: -0.0000

Data Index: 1134141 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.1398. Min Act: -0.0000

Data Index: 593061 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0870. Min Act: -0.0000

Data Index: 452779 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1543953 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0289. Min Act: -0.0000

Data Index: 135491 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0957. Min Act: -0.0000

Data Index: 390259 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0205. Min Act: -0.0000

Data Index: 751852 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0413. Min Act: -0.0000

Data Index: 1129671 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 1.3076. Min Range: -1.3076

Max Act: 0.9490. Min Act: -0.0000

Data Index: 117306 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.3076. Min Range: -1.3076

Max Act: 0.9604. Min Act: -0.0000

Data Index: 461706 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 1.3076. Min Range: -1.3076

Max Act: 1.0475. Min Act: -0.0000

Data Index: 346623 (C4 (Web Text))

Max Activating Token Index: 13