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

Dataset: The Pile

Neuron 4241 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4297. Min Range: -3.4297

Max Act: 3.4297. Min Act: -0.0000

Data Index: 1179073 (The Pile)

Max Activating Token Index: 308

Text #1

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.5449. Min Act: -0.0000

Data Index: 284836 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.7149. Min Act: -0.0000

Data Index: 1584705 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.3166. Min Act: -0.0000

Data Index: 325124 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.5787. Min Act: -0.0000

Data Index: 1155045 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.9410. Min Act: -0.0000

Data Index: 211314 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.6126. Min Act: -0.0000

Data Index: 509328 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.3296. Min Act: -0.0000

Data Index: 1112515 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.8830. Min Act: -0.0000

Data Index: 1510737 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.9974. Min Act: -0.0000

Data Index: 135267 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.0229. Min Act: -0.0000

Data Index: 722589 (The Pile)

Max Activating Token Index: 923

Text #11

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.1056. Min Act: -0.0000

Data Index: 1197581 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.9487. Min Act: -0.0000

Data Index: 808678 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.6434. Min Act: -0.0000

Data Index: 951583 (The Pile)

Max Activating Token Index: 849

Text #14

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.8054. Min Act: -0.0000

Data Index: 374537 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.5531. Min Act: -0.0000

Data Index: 502553 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.7301. Min Act: -0.0000

Data Index: 111490 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.8538. Min Act: -0.0000

Data Index: 1326059 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 3.4297. Min Range: -3.4297

Max Act: 1.8851. Min Act: -0.0000

Data Index: 1488302 (The Pile)

Max Activating Token Index: 187

Text #19

Max Range: 3.4297. Min Range: -3.4297

Max Act: 2.0763. Min Act: -0.0000

Data Index: 131766 (The Pile)

Max Activating Token Index: 685