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

Dataset: The Pile

Neuron 4666 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1692891 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.4805. Min Act: -0.0000

Data Index: 749677 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.3359. Min Act: -0.0000

Data Index: 498138 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2581. Min Act: -0.0000

Data Index: 240829 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2307. Min Act: -0.0000

Data Index: 1901123 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.2739. Min Act: -0.0000

Data Index: 218300 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1816. Min Act: -0.0000

Data Index: 1181305 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1283. Min Act: -0.0000

Data Index: 931633 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1333. Min Act: -0.0000

Data Index: 1581205 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1805146 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1316949 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1181. Min Act: -0.0000

Data Index: 484409 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1469568 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0787. Min Act: -0.0000

Data Index: 699467 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0786. Min Act: -0.0000

Data Index: 52008 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0603. Min Act: -0.0000

Data Index: 682345 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1398071 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1288292 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1727073 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 1.5261. Min Range: -1.5261

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1504316 (The Pile)

Max Activating Token Index: 503