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

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

Neuron 1203 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: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0006

Data Index: 125988 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0466. Min Act: -0.0006

Data Index: 598339 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0456. Min Act: -0.0006

Data Index: 643062 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0451. Min Act: -0.0006

Data Index: 102571 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0431. Min Act: -0.0006

Data Index: 1338824 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0429. Min Act: -0.0006

Data Index: 1178312 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0442. Min Act: -0.0006

Data Index: 21905 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0439. Min Act: -0.0006

Data Index: 327347 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0432. Min Act: -0.0006

Data Index: 601700 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0414. Min Act: -0.0006

Data Index: 802069 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0423. Min Act: -0.0006

Data Index: 577784 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0414. Min Act: -0.0006

Data Index: 1193639 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0411. Min Act: -0.0006

Data Index: 599717 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0408. Min Act: -0.0006

Data Index: 1269158 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0396. Min Act: -0.0006

Data Index: 1045187 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0385. Min Act: -0.0006

Data Index: 263160 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0386. Min Act: -0.0006

Data Index: 724255 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1247518 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0397. Min Act: -0.0006

Data Index: 428848 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0394. Min Act: -0.0006

Data Index: 681976 (C4 (Web Text))

Max Activating Token Index: 890