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

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

Neuron 3719 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.8868. Min Act: -0.0001

Data Index: 1563306 (Python Code)

Max Activating Token Index: 528

Text #1

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.7743. Min Act: -0.0001

Data Index: 1563927 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.5032. Min Act: -0.0000

Data Index: 334866 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.4043. Min Act: -0.0001

Data Index: 189907 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3913. Min Act: -0.0000

Data Index: 1590145 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3967. Min Act: -0.0001

Data Index: 1639510 (Python Code)

Max Activating Token Index: 48

Text #6

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.4466. Min Act: -0.0001

Data Index: 1544151 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3861. Min Act: -0.0001

Data Index: 1590963 (Python Code)

Max Activating Token Index: 55

Text #8

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.4097. Min Act: -0.0001

Data Index: 595344 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3601. Min Act: -0.0001

Data Index: 344106 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3881. Min Act: -0.0001

Data Index: 1280897 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3049. Min Act: -0.0001

Data Index: 405256 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3179. Min Act: -0.0001

Data Index: 618577 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3767. Min Act: -0.0001

Data Index: 814600 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3357. Min Act: -0.0001

Data Index: 1471430 (Python Code)

Max Activating Token Index: 509

Text #15

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3016. Min Act: -0.0001

Data Index: 33965 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.2573. Min Act: -0.0000

Data Index: 534241 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.3665. Min Act: -0.0001

Data Index: 1363026 (Python Code)

Max Activating Token Index: 44

Text #18

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.1433. Min Act: -0.0001

Data Index: 14699 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 1.8868. Min Range: -1.8868

Max Act: 1.2713. Min Act: -0.0001

Data Index: 1218511 (C4 (Web Text))

Max Activating Token Index: 402