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

Dataset: The Pile

Neuron 172 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: 1.9166. Min Range: -1.9166

Max Act: 1.8402. Min Act: -0.0000

Data Index: 1336877 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.9166. Min Act: -0.0000

Data Index: 1532078 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5289. Min Act: -0.0000

Data Index: 532148 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.8265. Min Act: -0.0000

Data Index: 345079 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.7173. Min Act: -0.0000

Data Index: 431815 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1311835 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.2902. Min Act: -0.0000

Data Index: 1067764 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.3595. Min Act: -0.0000

Data Index: 1186652 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6651. Min Act: -0.0000

Data Index: 902859 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.6755. Min Act: -0.0000

Data Index: 1096423 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5725. Min Act: -0.0000

Data Index: 158202 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4513. Min Act: -0.0000

Data Index: 898404 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.5179. Min Act: -0.0000

Data Index: 219622 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4319. Min Act: -0.0000

Data Index: 424310 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4645. Min Act: -0.0000

Data Index: 481973 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.1548. Min Act: -0.0000

Data Index: 1932456 (The Pile)

Max Activating Token Index: 917

Text #16

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.3343. Min Act: -0.0000

Data Index: 131726 (The Pile)

Max Activating Token Index: 504

Text #17

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1722389 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1675890 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 1.9166. Min Range: -1.9166

Max Act: 1.4285. Min Act: -0.0000

Data Index: 659858 (The Pile)

Max Activating Token Index: 175