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

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

Neuron 2999 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7580. Min Act: -0.0000

Data Index: 607550 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.7253. Min Act: -0.0000

Data Index: 496212 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1609477 (Python Code)

Max Activating Token Index: 852

Text #3

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.6441. Min Act: -0.0000

Data Index: 930180 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5802. Min Act: -0.0000

Data Index: 720582 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5808. Min Act: -0.0000

Data Index: 588485 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5817. Min Act: -0.0000

Data Index: 958203 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1442193 (Python Code)

Max Activating Token Index: 631

Text #8

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1515401 (Python Code)

Max Activating Token Index: 642

Text #9

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4671. Min Act: -0.0000

Data Index: 792061 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4707. Min Act: -0.0000

Data Index: 932891 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4679. Min Act: -0.0000

Data Index: 938679 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4466. Min Act: 0.0000

Data Index: 1079016 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1485945 (Python Code)

Max Activating Token Index: 655

Text #14

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4418. Min Act: -0.0000

Data Index: 473846 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1431754 (Python Code)

Max Activating Token Index: 619

Text #16

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1541452 (Python Code)

Max Activating Token Index: 697

Text #17

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4254. Min Act: -0.0000

Data Index: 343079 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1022036 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.7580. Min Range: -0.7580

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1007940 (C4 (Web Text))

Max Activating Token Index: 311