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

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

Neuron 1500 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0463. Min Act: -0.0003

Data Index: 839288 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0376. Min Act: -0.0003

Data Index: 528266 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0373. Min Act: -0.0004

Data Index: 733404 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1340463 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0404. Min Act: -0.0003

Data Index: 451660 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0360. Min Act: -0.0003

Data Index: 170502 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1358854 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1037114 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0346. Min Act: -0.0003

Data Index: 225383 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0357. Min Act: -0.0003

Data Index: 639725 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0345. Min Act: -0.0003

Data Index: 755324 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0338. Min Act: -0.0003

Data Index: 670720 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0325. Min Act: -0.0003

Data Index: 461739 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0325. Min Act: -0.0003

Data Index: 157368 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0297. Min Act: -0.0003

Data Index: 862812 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0343. Min Act: -0.0003

Data Index: 353558 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0322. Min Act: -0.0003

Data Index: 726229 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1335688 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1014122 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0327. Min Act: -0.0003

Data Index: 932172 (C4 (Web Text))

Max Activating Token Index: 432