Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1508 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0357. Min Act: -0.0002

Data Index: 926737 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0002

Data Index: 839782 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0398. Min Act: -0.0002

Data Index: 955176 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0344. Min Act: -0.0002

Data Index: 38321 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0349. Min Act: -0.0002

Data Index: 638877 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1136987 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1182810 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0310. Min Act: -0.0002

Data Index: 597009 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1305104 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1294754 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0329. Min Act: -0.0002

Data Index: 237250 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0286. Min Act: -0.0002

Data Index: 584571 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1129388 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0281. Min Act: -0.0002

Data Index: 229383 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0301. Min Act: -0.0002

Data Index: 375029 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0280. Min Act: -0.0002

Data Index: 258904 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0270. Min Act: -0.0002

Data Index: 364415 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0273. Min Act: -0.0002

Data Index: 832683 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0279. Min Act: -0.0002

Data Index: 41541 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1273259 (C4 (Web Text))

Max Activating Token Index: 404