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

Dataset: The Pile

Neuron 2920 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.5801. Min Act: -0.0000

Data Index: 707817 (The Pile)

Max Activating Token Index: 749

Text #1

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.7460. Min Act: -0.0000

Data Index: 85880 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.7291. Min Act: -0.0000

Data Index: 1021644 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.5172. Min Act: -0.0000

Data Index: 780988 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1357715 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.5507. Min Act: -0.0000

Data Index: 1753448 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1884037 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4372. Min Act: -0.0000

Data Index: 333814 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4954. Min Act: -0.0000

Data Index: 898927 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4792. Min Act: -0.0000

Data Index: 25896 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4610. Min Act: -0.0000

Data Index: 390065 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4298. Min Act: -0.0000

Data Index: 1551597 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4361. Min Act: -0.0000

Data Index: 137908 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4306. Min Act: -0.0000

Data Index: 328699 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1961369 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.4217. Min Act: -0.0000

Data Index: 704157 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.3122. Min Act: -0.0000

Data Index: 1826121 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.3057. Min Act: -0.0000

Data Index: 1224897 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.2519. Min Act: -0.0000

Data Index: 325854 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 1.7460. Min Range: -1.7460

Max Act: 1.3758. Min Act: -0.0000

Data Index: 890785 (The Pile)

Max Activating Token Index: 303