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

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

Neuron 2262 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0002

Data Index: 780642 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1104398 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0591. Min Act: -0.0003

Data Index: 472165 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0577. Min Act: -0.0003

Data Index: 519332 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0594. Min Act: -0.0003

Data Index: 482198 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1234630 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0420. Min Act: -0.0002

Data Index: 383554 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0368. Min Act: -0.0002

Data Index: 841357 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0356. Min Act: -0.0002

Data Index: 854655 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0376. Min Act: -0.0002

Data Index: 513438 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0416. Min Act: -0.0002

Data Index: 793169 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0337. Min Act: -0.0002

Data Index: 618111 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0348. Min Act: -0.0002

Data Index: 978878 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0335. Min Act: -0.0002

Data Index: 903568 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0350. Min Act: -0.0002

Data Index: 42182 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1350732 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0369. Min Act: -0.0002

Data Index: 891395 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1054173 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0307. Min Act: -0.0002

Data Index: 895078 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0354. Min Act: -0.0002

Data Index: 396887 (C4 (Web Text))

Max Activating Token Index: 98