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

Dataset: The Pile

Neuron 1159 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1368271 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4586. Min Act: -0.0000

Data Index: 990127 (The Pile)

Max Activating Token Index: 661

Text #2

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4301. Min Act: 0.0000

Data Index: 1310503 (The Pile)

Max Activating Token Index: 258

Text #3

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4199. Min Act: -0.0000

Data Index: 429834 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1424651 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.4172. Min Act: 0.0000

Data Index: 1776772 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3991. Min Act: -0.0000

Data Index: 479881 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1224817 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1150203 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1647213 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3841. Min Act: -0.0000

Data Index: 458973 (The Pile)

Max Activating Token Index: 966

Text #11

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3755. Min Act: -0.0000

Data Index: 166832 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1206391 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3711. Min Act: -0.0000

Data Index: 459591 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3828. Min Act: 0.0000

Data Index: 524587 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1443221 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3577. Min Act: -0.0000

Data Index: 687021 (The Pile)

Max Activating Token Index: 647

Text #17

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1295868 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3444. Min Act: -0.0000

Data Index: 297814 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1170740 (The Pile)

Max Activating Token Index: 547