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

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

Neuron 638 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: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0006

Data Index: 453491 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0484. Min Act: -0.0006

Data Index: 766196 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0392. Min Act: -0.0006

Data Index: 104321 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0390. Min Act: -0.0006

Data Index: 115066 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1355520 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0384. Min Act: -0.0006

Data Index: 170725 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0389. Min Act: -0.0006

Data Index: 468670 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0393. Min Act: -0.0006

Data Index: 1170904 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0370. Min Act: -0.0006

Data Index: 771677 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0363. Min Act: -0.0006

Data Index: 340708 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0368. Min Act: -0.0006

Data Index: 408594 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1336777 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0348. Min Act: -0.0006

Data Index: 575840 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0337. Min Act: -0.0006

Data Index: 638406 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0342. Min Act: -0.0006

Data Index: 600225 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0349. Min Act: -0.0006

Data Index: 888 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0340. Min Act: -0.0006

Data Index: 1057828 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0340. Min Act: -0.0006

Data Index: 249869 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0339. Min Act: -0.0006

Data Index: 1335508 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0324. Min Act: -0.0006

Data Index: 254282 (C4 (Web Text))

Max Activating Token Index: 323