Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1870 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0005

Data Index: 1030534 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0388. Min Act: -0.0005

Data Index: 1334100 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0378. Min Act: -0.0005

Data Index: 800421 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0364. Min Act: -0.0005

Data Index: 130763 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0342. Min Act: -0.0005

Data Index: 693783 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0345. Min Act: -0.0005

Data Index: 794965 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0336. Min Act: -0.0005

Data Index: 521339 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0341. Min Act: -0.0005

Data Index: 581956 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0334. Min Act: -0.0005

Data Index: 944433 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0338. Min Act: -0.0005

Data Index: 807873 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0326. Min Act: -0.0005

Data Index: 331315 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0330. Min Act: -0.0005

Data Index: 640675 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0317. Min Act: -0.0005

Data Index: 1358337 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0352. Min Act: -0.0005

Data Index: 1341770 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0339. Min Act: -0.0005

Data Index: 271805 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0336. Min Act: -0.0005

Data Index: 938140 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0321. Min Act: -0.0005

Data Index: 771594 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0344. Min Act: -0.0005

Data Index: 1217968 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0317. Min Act: -0.0005

Data Index: 976772 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0327. Min Act: -0.0005

Data Index: 126923 (C4 (Web Text))

Max Activating Token Index: 829