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

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

Neuron 5623 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.4062. Min Act: -0.0000

Data Index: 1497272 (Python Code)

Max Activating Token Index: 526

Text #1

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3933. Min Act: -0.0000

Data Index: 1626611 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.4887. Min Act: -0.0000

Data Index: 1561307 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.4187. Min Act: -0.0000

Data Index: 1622403 (Python Code)

Max Activating Token Index: 528

Text #4

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1625690 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1466753 (Python Code)

Max Activating Token Index: 454

Text #6

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.4156. Min Act: -0.0000

Data Index: 621446 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1460932 (Python Code)

Max Activating Token Index: 271

Text #8

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.4059. Min Act: -0.0000

Data Index: 1460512 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1510926 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1627873 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1376456 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1596799 (Python Code)

Max Activating Token Index: 557

Text #13

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3659. Min Act: -0.0000

Data Index: 1522586 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1545406 (Python Code)

Max Activating Token Index: 784

Text #15

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3264. Min Act: -0.0000

Data Index: 1486210 (Python Code)

Max Activating Token Index: 543

Text #16

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3214. Min Act: -0.0000

Data Index: 1448209 (Python Code)

Max Activating Token Index: 792

Text #17

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1518251 (Python Code)

Max Activating Token Index: 607

Text #18

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3440. Min Act: -0.0000

Data Index: 965517 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.4887. Min Range: -1.4887

Max Act: 1.3572. Min Act: -0.0000

Data Index: 1501563 (Python Code)

Max Activating Token Index: 494