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

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

Neuron 28 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: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0006

Data Index: 254373 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0423. Min Act: -0.0006

Data Index: 190476 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0407. Min Act: -0.0006

Data Index: 117868 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0384. Min Act: -0.0006

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0378. Min Act: -0.0006

Data Index: 1355055 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0359. Min Act: -0.0006

Data Index: 691844 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0372. Min Act: -0.0006

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0377. Min Act: -0.0006

Data Index: 383346 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0371. Min Act: -0.0006

Data Index: 517272 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0364. Min Act: -0.0006

Data Index: 546371 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0344. Min Act: -0.0006

Data Index: 227994 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0345. Min Act: -0.0006

Data Index: 110842 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0344. Min Act: -0.0006

Data Index: 388798 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0341. Min Act: -0.0006

Data Index: 11410 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0338. Min Act: -0.0006

Data Index: 614682 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0323. Min Act: -0.0006

Data Index: 726343 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0320. Min Act: -0.0006

Data Index: 252853 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0348. Min Act: -0.0006

Data Index: 444872 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0337. Min Act: -0.0006

Data Index: 844585 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0357. Min Act: -0.0006

Data Index: 944783 (C4 (Web Text))

Max Activating Token Index: 459