Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2068 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.6226. Min Act: -0.0000

Data Index: 537871 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.5587. Min Act: -0.0000

Data Index: 267753 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.4452. Min Act: -0.0000

Data Index: 1065873 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.4041. Min Act: -0.0000

Data Index: 725270 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3951. Min Act: -0.0000

Data Index: 391669 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.4097. Min Act: -0.0000

Data Index: 45876 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3725. Min Act: -0.0000

Data Index: 468628 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3615. Min Act: -0.0000

Data Index: 636739 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3431. Min Act: -0.0000

Data Index: 687329 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3112. Min Act: -0.0000

Data Index: 384065 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3725. Min Act: -0.0000

Data Index: 216177 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3096. Min Act: -0.0000

Data Index: 961365 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3157. Min Act: -0.0000

Data Index: 1181351 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.2583. Min Act: -0.0000

Data Index: 116525 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.2876. Min Act: -0.0000

Data Index: 184847 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1090183 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1359546 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.2666. Min Act: -0.0000

Data Index: 107851 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.2694. Min Act: -0.0000

Data Index: 68807 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.2244. Min Act: -0.0000

Data Index: 979554 (C4 (Web Text))

Max Activating Token Index: 112