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

Dataset: The Pile

Neuron 2827 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.8108. Min Act: -0.0000

Data Index: 963621 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.6297. Min Act: -0.0000

Data Index: 148314 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.5035. Min Act: -0.0000

Data Index: 31346 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.3411. Min Act: -0.0000

Data Index: 449312 (The Pile)

Max Activating Token Index: 684

Text #4

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1339747 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.5729. Min Act: -0.0000

Data Index: 1040321 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.3320. Min Act: -0.0000

Data Index: 282104 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.1974. Min Act: -0.0000

Data Index: 709160 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1104438 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.2037. Min Act: 0.0000

Data Index: 892020 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.1817. Min Act: -0.0000

Data Index: 119063 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.3173. Min Act: -0.0000

Data Index: 269568 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.2273. Min Act: -0.0000

Data Index: 442188 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1251478 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.1757. Min Act: -0.0000

Data Index: 120367 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1805836 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.2329. Min Act: -0.0000

Data Index: 328537 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1805933 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1744447 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 1.8108. Min Range: -1.8108

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1273221 (The Pile)

Max Activating Token Index: 494