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

Dataset: The Pile

Neuron 627 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.1327. Min Act: -0.0000

Data Index: 1868999 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.6859. Min Act: -0.0000

Data Index: 1168879 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.4469. Min Act: -0.0000

Data Index: 242350 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.6875. Min Act: -0.0000

Data Index: 1545280 (The Pile)

Max Activating Token Index: 285

Text #4

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.5110. Min Act: -0.0000

Data Index: 113327 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.4084. Min Act: -0.0000

Data Index: 1137297 (The Pile)

Max Activating Token Index: 39

Text #6

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.1657. Min Act: -0.0000

Data Index: 965868 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.2797. Min Act: -0.0000

Data Index: 778501 (The Pile)

Max Activating Token Index: 92

Text #8

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.2594. Min Act: -0.0000

Data Index: 333311 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.2549. Min Act: -0.0000

Data Index: 1380033 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.2301. Min Act: -0.0000

Data Index: 1868045 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.0986. Min Act: -0.0000

Data Index: 343071 (The Pile)

Max Activating Token Index: 627

Text #12

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.1799. Min Act: -0.0000

Data Index: 1156347 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.9570. Min Act: -0.0000

Data Index: 675853 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.1859. Min Act: -0.0000

Data Index: 664887 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.2845. Min Act: -0.0000

Data Index: 1366087 (The Pile)

Max Activating Token Index: 261

Text #16

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.1655. Min Act: -0.0000

Data Index: 1719339 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.2753. Min Act: -0.0000

Data Index: 1982723 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.1402. Min Act: -0.0000

Data Index: 1836009 (The Pile)

Max Activating Token Index: 512

Text #19

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.1142. Min Act: -0.0000

Data Index: 1679066 (The Pile)

Max Activating Token Index: 202