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

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

Neuron 628 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0006

Data Index: 78096 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0391. Min Act: -0.0006

Data Index: 403367 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0375. Min Act: -0.0006

Data Index: 630229 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0371. Min Act: -0.0006

Data Index: 64760 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0361. Min Act: -0.0006

Data Index: 301995 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0371. Min Act: -0.0006

Data Index: 20315 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1100538 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0346. Min Act: -0.0006

Data Index: 1336688 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1245319 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0302. Min Act: -0.0006

Data Index: 196387 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0325. Min Act: -0.0006

Data Index: 222662 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0328. Min Act: -0.0006

Data Index: 197701 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0324. Min Act: -0.0006

Data Index: 156774 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0318. Min Act: -0.0006

Data Index: 203260 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1090915 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0282. Min Act: -0.0006

Data Index: 806899 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0297. Min Act: -0.0006

Data Index: 871 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0297. Min Act: -0.0006

Data Index: 935993 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0289. Min Act: -0.0006

Data Index: 492049 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0283. Min Act: -0.0006

Data Index: 669505 (C4 (Web Text))

Max Activating Token Index: 714