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

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

Neuron 3198 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.7289. Min Act: -0.0000

Data Index: 359480 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6760. Min Act: 0.0001

Data Index: 960264 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1060821 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1107601 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5852. Min Act: -0.0000

Data Index: 779010 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5736. Min Act: -0.0000

Data Index: 204272 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5296. Min Act: -0.0000

Data Index: 106872 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5741. Min Act: 0.0000

Data Index: 1284704 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5372. Min Act: -0.0000

Data Index: 679135 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1095020 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1010088 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5416. Min Act: -0.0000

Data Index: 144575 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5335. Min Act: -0.0000

Data Index: 104450 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5192. Min Act: -0.0000

Data Index: 431539 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5154. Min Act: -0.0000

Data Index: 55392 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4993. Min Act: 0.0001

Data Index: 824578 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4648. Min Act: -0.0000

Data Index: 306451 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4756. Min Act: 0.0001

Data Index: 887539 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1335166 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4216. Min Act: 0.0000

Data Index: 1352166 (C4 (Web Text))

Max Activating Token Index: 829