Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2712 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1442125 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1588534 (Python Code)

Max Activating Token Index: 605

Text #2

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1387080 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1598976 (Python Code)

Max Activating Token Index: 357

Text #4

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1432479 (Python Code)

Max Activating Token Index: 527

Text #5

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1625734 (Python Code)

Max Activating Token Index: 482

Text #6

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1494671 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.4629. Min Act: -0.0001

Data Index: 1463486 (Python Code)

Max Activating Token Index: 554

Text #8

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.4624. Min Act: -0.0001

Data Index: 1580517 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1626506 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.4357. Min Act: -0.0001

Data Index: 1463341 (Python Code)

Max Activating Token Index: 302

Text #11

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1420108 (Python Code)

Max Activating Token Index: 819

Text #12

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.4428. Min Act: -0.0000

Data Index: 666366 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.4596. Min Act: -0.0001

Data Index: 1373581 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.3943. Min Act: -0.0001

Data Index: 1453983 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1385808 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1266443 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1442613 (Python Code)

Max Activating Token Index: 934

Text #18

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1635670 (Python Code)

Max Activating Token Index: 944

Text #19

Max Range: 0.9454. Min Range: -0.9454

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1547352 (Python Code)

Max Activating Token Index: 757