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

Dataset: The Pile

Neuron 2090 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2754. Min Act: -0.0000

Data Index: 1815935 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1938630 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.3403. Min Act: -0.0000

Data Index: 903048 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1417457 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1662. Min Act: -0.0000

Data Index: 562951 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.2878. Min Act: -0.0000

Data Index: 709687 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1552. Min Act: -0.0000

Data Index: 616778 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1699. Min Act: -0.0000

Data Index: 482431 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0038. Min Act: -0.0000

Data Index: 351243 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1841246 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1196198 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0588. Min Act: -0.0000

Data Index: 232670 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1811. Min Act: -0.0000

Data Index: 663264 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1076543 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0996. Min Act: -0.0000

Data Index: 27656 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0575. Min Act: -0.0000

Data Index: 188800 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9101. Min Act: -0.0000

Data Index: 114840 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9601. Min Act: -0.0000

Data Index: 317015 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 1.3403. Min Range: -1.3403

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1605129 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 1.3403. Min Range: -1.3403

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1806123 (The Pile)

Max Activating Token Index: 501