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

Dataset: The Pile

Neuron 682 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.4282. Min Act: -0.0000

Data Index: 1543234 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.3710. Min Act: -0.0000

Data Index: 1644230 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1100284 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1279095 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.3774. Min Act: -0.0000

Data Index: 50015 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.3134. Min Act: -0.0000

Data Index: 236342 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1555330 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2529. Min Act: -0.0000

Data Index: 764807 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1935282 (The Pile)

Max Activating Token Index: 796

Text #9

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2293. Min Act: -0.0000

Data Index: 734469 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2150. Min Act: -0.0000

Data Index: 876237 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2355. Min Act: -0.0000

Data Index: 69965 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2110. Min Act: -0.0000

Data Index: 1655196 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1960. Min Act: -0.0000

Data Index: 136237 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1230244 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2045. Min Act: -0.0000

Data Index: 721053 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1026. Min Act: -0.0000

Data Index: 563990 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1879721 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1599. Min Act: -0.0000

Data Index: 623917 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1008. Min Act: -0.0000

Data Index: 251066 (The Pile)

Max Activating Token Index: 776