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

Dataset: The Pile

Neuron 4434 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: 0.1546. Min Range: -0.1546

Max Act: 0.1546. Min Act: -0.0000

Data Index: 356893 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1304. Min Act: -0.0000

Data Index: 241049 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1787959 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1319. Min Act: -0.0000

Data Index: 140319 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1284. Min Act: -0.0000

Data Index: 812434 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1277. Min Act: -0.0000

Data Index: 645093 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1520947 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1117. Min Act: -0.0000

Data Index: 495179 (The Pile)

Max Activating Token Index: 880

Text #8

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1224. Min Act: -0.0000

Data Index: 350518 (The Pile)

Max Activating Token Index: 391

Text #9

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1229109 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1171. Min Act: -0.0000

Data Index: 774765 (The Pile)

Max Activating Token Index: 169

Text #11

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1570620 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1087. Min Act: -0.0000

Data Index: 883338 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1715039 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1183. Min Act: -0.0000

Data Index: 345411 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1171. Min Act: -0.0000

Data Index: 945616 (The Pile)

Max Activating Token Index: 434

Text #16

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1717433 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1885200 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1089060 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 0.1546. Min Range: -0.1546

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1053978 (The Pile)

Max Activating Token Index: 68