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

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

Neuron 3391 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1390370 (Python Code)

Max Activating Token Index: 130

Text #1

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0409. Min Act: -0.0001

Data Index: 236142 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0406. Min Act: -0.0001

Data Index: 1495328 (Python Code)

Max Activating Token Index: 298

Text #3

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0405. Min Act: -0.0001

Data Index: 359838 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1374276 (Python Code)

Max Activating Token Index: 567

Text #5

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1089879 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1462618 (Python Code)

Max Activating Token Index: 734

Text #7

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0381. Min Act: -0.0001

Data Index: 636044 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0363. Min Act: -0.0001

Data Index: 934837 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1496346 (Python Code)

Max Activating Token Index: 469

Text #10

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1610716 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0356. Min Act: -0.0001

Data Index: 35107 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1418951 (Python Code)

Max Activating Token Index: 247

Text #13

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1039712 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0356. Min Act: -0.0001

Data Index: 832525 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1543232 (Python Code)

Max Activating Token Index: 639

Text #16

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0352. Min Act: -0.0001

Data Index: 652226 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0354. Min Act: -0.0001

Data Index: 246316 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1521335 (Python Code)

Max Activating Token Index: 902

Text #19

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0349. Min Act: -0.0001

Data Index: 492815 (C4 (Web Text))

Max Activating Token Index: 228