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

Dataset: The Pile

Neuron 1177 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: 1.6191. Min Range: -1.6191

Max Act: 1.6191. Min Act: -0.0000

Data Index: 1396851 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.4931. Min Act: -0.0000

Data Index: 724146 (The Pile)

Max Activating Token Index: 195

Text #2

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.6133. Min Act: -0.0000

Data Index: 962356 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1525399 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.5777. Min Act: -0.0000

Data Index: 1692376 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.5608. Min Act: -0.0000

Data Index: 431734 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.3999. Min Act: -0.0000

Data Index: 708528 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.5588. Min Act: -0.0000

Data Index: 10522 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.4346. Min Act: -0.0000

Data Index: 868601 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.3906. Min Act: -0.0000

Data Index: 267457 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1540509 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.4513. Min Act: -0.0000

Data Index: 1294243 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.4489. Min Act: -0.0000

Data Index: 1389007 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.4114. Min Act: -0.0000

Data Index: 229379 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.4025. Min Act: -0.0000

Data Index: 604820 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.3874. Min Act: -0.0000

Data Index: 549215 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.4371. Min Act: -0.0000

Data Index: 109262 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.3687. Min Act: -0.0000

Data Index: 514400 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.3337. Min Act: -0.0000

Data Index: 1995285 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.6191. Min Range: -1.6191

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1487528 (The Pile)

Max Activating Token Index: 607