Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 597 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0514. Min Act: -0.0004

Data Index: 357312 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1124450 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0433. Min Act: -0.0002

Data Index: 49223 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0405. Min Act: -0.0003

Data Index: 235376 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0419. Min Act: -0.0003

Data Index: 283143 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0414. Min Act: -0.0004

Data Index: 100447 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0406. Min Act: -0.0001

Data Index: 3622 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0384. Min Act: -0.0003

Data Index: 323628 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0385. Min Act: -0.0002

Data Index: 35679 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0384. Min Act: -0.0003

Data Index: 393664 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0390. Min Act: -0.0003

Data Index: 774074 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1248735 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1342913 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0360. Min Act: -0.0003

Data Index: 324484 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0372. Min Act: -0.0003

Data Index: 228603 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1011097 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0360. Min Act: -0.0002

Data Index: 686243 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1056342 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0355. Min Act: -0.0003

Data Index: 166523 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0339. Min Act: -0.0002

Data Index: 766013 (C4 (Web Text))

Max Activating Token Index: 894