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

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

Neuron 5300 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.5644. Min Act: -0.0000

Data Index: 283105 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.5539. Min Act: -0.0000

Data Index: 162828 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.6586. Min Act: -0.0000

Data Index: 767702 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.3948. Min Act: -0.0000

Data Index: 1028793 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.4875. Min Act: -0.0000

Data Index: 1246241 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.3851. Min Act: -0.0000

Data Index: 72674 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.4028. Min Act: -0.0000

Data Index: 512317 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.2222. Min Act: -0.0000

Data Index: 362080 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.3640. Min Act: -0.0000

Data Index: 885997 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.3325. Min Act: -0.0000

Data Index: 580170 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.3302. Min Act: -0.0000

Data Index: 662962 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.4684. Min Act: -0.0000

Data Index: 445119 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.1443. Min Act: -0.0000

Data Index: 178101 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.1239. Min Act: -0.0000

Data Index: 166765 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.3644. Min Act: -0.0000

Data Index: 812252 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.2124. Min Act: -0.0000

Data Index: 460505 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.3066. Min Act: -0.0000

Data Index: 967135 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.2986. Min Act: -0.0000

Data Index: 129701 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.1628. Min Act: -0.0000

Data Index: 843991 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 2.6586. Min Range: -2.6586

Max Act: 2.1740. Min Act: -0.0000

Data Index: 551142 (C4 (Web Text))

Max Activating Token Index: 516