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

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

Neuron 3114 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0923. Min Range: -2.0923

Max Act: 2.0923. Min Act: -0.0000

Data Index: 1274989 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.9026. Min Act: -0.0000

Data Index: 991537 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.7218. Min Act: -0.0000

Data Index: 1040792 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.6083. Min Act: -0.0000

Data Index: 52916 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.4663. Min Act: -0.0000

Data Index: 160223 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.4636. Min Act: -0.0000

Data Index: 643055 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.5100. Min Act: -0.0000

Data Index: 670127 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.2242. Min Act: -0.0000

Data Index: 600115 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.2133. Min Act: -0.0000

Data Index: 769536 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1027701 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1216062 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.1736. Min Act: -0.0000

Data Index: 1028786 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.1673. Min Act: -0.0000

Data Index: 19488 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.1409. Min Act: -0.0000

Data Index: 659493 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.0484. Min Act: -0.0000

Data Index: 358590 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.0380. Min Act: -0.0000

Data Index: 269461 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 2.0923. Min Range: -2.0923

Max Act: 0.9169. Min Act: -0.0000

Data Index: 998348 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 2.0923. Min Range: -2.0923

Max Act: 0.8558. Min Act: -0.0000

Data Index: 479409 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.0079. Min Act: -0.0000

Data Index: 56624 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 2.0923. Min Range: -2.0923

Max Act: 1.0610. Min Act: -0.0000

Data Index: 73147 (C4 (Web Text))

Max Activating Token Index: 516