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

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

Neuron 1696 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.7389. Min Act: -0.0000

Data Index: 15654 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.5585. Min Act: -0.0000

Data Index: 860546 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4587. Min Act: -0.0000

Data Index: 111868 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4332. Min Act: -0.0000

Data Index: 1129893 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4871. Min Act: -0.0000

Data Index: 770348 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4010. Min Act: -0.0000

Data Index: 490559 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1151934 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4776. Min Act: -0.0000

Data Index: 933181 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4392. Min Act: -0.0000

Data Index: 310189 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4399. Min Act: -0.0000

Data Index: 7817 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1148609 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4233. Min Act: -0.0000

Data Index: 364868 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4144. Min Act: -0.0000

Data Index: 319075 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4275. Min Act: -0.0000

Data Index: 557613 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.3481. Min Act: -0.0000

Data Index: 547284 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4046. Min Act: -0.0000

Data Index: 7713 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4084. Min Act: -0.0000

Data Index: 515162 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4900. Min Act: -0.0000

Data Index: 87966 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.3875. Min Act: -0.0000

Data Index: 163606 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1123992 (C4 (Web Text))

Max Activating Token Index: 249