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

Dataset: The Pile

Neuron 743 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.6188. Min Act: -0.0000

Data Index: 434790 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5798. Min Act: -0.0000

Data Index: 777876 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1618949 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1261380 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5749. Min Act: -0.0000

Data Index: 991457 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1003804 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5643. Min Act: -0.0000

Data Index: 687859 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5591. Min Act: -0.0000

Data Index: 705122 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1261973 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1032488 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5540. Min Act: -0.0000

Data Index: 401266 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5323. Min Act: -0.0000

Data Index: 866539 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1146621 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1859783 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1541353 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5211. Min Act: -0.0000

Data Index: 574460 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1139545 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1225239 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1881569 (The Pile)

Max Activating Token Index: 196

Text #19

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4984. Min Act: -0.0000

Data Index: 820303 (The Pile)

Max Activating Token Index: 529