Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 451 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0006

Data Index: 512144 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0433. Min Act: -0.0005

Data Index: 1089174 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0413. Min Act: -0.0006

Data Index: 1086544 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0419. Min Act: -0.0005

Data Index: 625672 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0397. Min Act: -0.0006

Data Index: 560899 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0402. Min Act: -0.0006

Data Index: 1011512 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0388. Min Act: -0.0006

Data Index: 256078 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0396. Min Act: -0.0006

Data Index: 401196 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0385. Min Act: -0.0006

Data Index: 297063 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0392. Min Act: -0.0006

Data Index: 60516 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0382. Min Act: -0.0006

Data Index: 286680 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0388. Min Act: -0.0005

Data Index: 460150 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0365. Min Act: -0.0006

Data Index: 639131 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0378. Min Act: -0.0006

Data Index: 988300 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0383. Min Act: -0.0006

Data Index: 839944 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0376. Min Act: -0.0005

Data Index: 280589 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0356. Min Act: -0.0006

Data Index: 1098397 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0368. Min Act: -0.0006

Data Index: 803244 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0351. Min Act: -0.0006

Data Index: 701940 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0364. Min Act: -0.0006

Data Index: 437690 (C4 (Web Text))

Max Activating Token Index: 169