Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3156 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1252442 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0469. Min Act: -0.0001

Data Index: 205561 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0436. Min Act: -0.0001

Data Index: 601301 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1050468 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1110943 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0435. Min Act: -0.0001

Data Index: 297409 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0414. Min Act: -0.0001

Data Index: 337373 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1141612 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0398. Min Act: -0.0001

Data Index: 258593 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0416. Min Act: -0.0001

Data Index: 478080 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1535733 (Python Code)

Max Activating Token Index: 992

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0341. Min Act: -0.0001

Data Index: 679404 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1589657 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0394. Min Act: -0.0002

Data Index: 334606 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0390. Min Act: -0.0001

Data Index: 907784 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0310. Min Act: -0.0001

Data Index: 626059 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1474773 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0353. Min Act: -0.0001

Data Index: 155667 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0363. Min Act: -0.0001

Data Index: 727709 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0346. Min Act: -0.0001

Data Index: 707691 (C4 (Web Text))

Max Activating Token Index: 501