Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2088 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1681881 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1242228 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1995188 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1354634 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0232. Min Act: -0.0000

Data Index: 346866 (The Pile)

Max Activating Token Index: 57

Text #5

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1310890 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1806716 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1152382 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 1.2198. Min Range: -1.2198

Max Act: 1.0002. Min Act: -0.0000

Data Index: 220162 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1052668 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1412065 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1064730 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8873. Min Act: -0.0000

Data Index: 817297 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1624986 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1180125 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1204912 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.9301. Min Act: -0.0000

Data Index: 835860 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1534923 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1166877 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 1.2198. Min Range: -1.2198

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1050292 (The Pile)

Max Activating Token Index: 285