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

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

Neuron 180 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0003

Data Index: 409501 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0375. Min Act: -0.0003

Data Index: 247795 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0353. Min Act: -0.0003

Data Index: 425886 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0354. Min Act: -0.0003

Data Index: 683873 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0341. Min Act: -0.0003

Data Index: 320086 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1218886 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0345. Min Act: -0.0003

Data Index: 19592 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0342. Min Act: -0.0003

Data Index: 826120 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1199593 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0342. Min Act: -0.0003

Data Index: 433875 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0333. Min Act: -0.0003

Data Index: 705469 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0336. Min Act: -0.0003

Data Index: 976486 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1129856 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0346. Min Act: -0.0003

Data Index: 73973 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0328. Min Act: -0.0003

Data Index: 101089 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0327. Min Act: -0.0003

Data Index: 612838 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0330. Min Act: -0.0003

Data Index: 561591 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1018405 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0310. Min Act: -0.0003

Data Index: 285603 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1241461 (C4 (Web Text))

Max Activating Token Index: 56