Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 789 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0001

Data Index: 583288 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1055102 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1295128 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0420. Min Act: -0.0001

Data Index: 433303 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0368. Min Act: -0.0002

Data Index: 760015 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1531432 (Python Code)

Max Activating Token Index: 150

Text #6

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0384. Min Act: -0.0001

Data Index: 628532 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0380. Min Act: -0.0001

Data Index: 916030 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1154045 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1364202 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0321. Min Act: -0.0002

Data Index: 814928 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0347. Min Act: -0.0002

Data Index: 828024 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0342. Min Act: -0.0001

Data Index: 271074 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1340303 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0341. Min Act: -0.0001

Data Index: 501035 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1392475 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1608626 (Python Code)

Max Activating Token Index: 932

Text #17

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0354. Min Act: -0.0001

Data Index: 199684 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0353. Min Act: -0.0001

Data Index: 961172 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0341. Min Act: -0.0002

Data Index: 548959 (C4 (Web Text))

Max Activating Token Index: 198