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

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

Neuron 3799 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: 4.0177. Min Range: -4.0177

Max Act: 4.0177. Min Act: -0.0000

Data Index: 1300914 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.5795. Min Act: -0.0000

Data Index: 1140424 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.7544. Min Act: -0.0000

Data Index: 757112 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.4211. Min Act: -0.0000

Data Index: 106665 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.2006. Min Act: -0.0000

Data Index: 49265 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.2022. Min Act: -0.0000

Data Index: 1359346 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.1716. Min Act: -0.0000

Data Index: 1265688 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.1453. Min Act: -0.0000

Data Index: 1167858 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.0561. Min Act: -0.0000

Data Index: 1355918 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 4.0177. Min Range: -4.0177

Max Act: 3.0195. Min Act: -0.0000

Data Index: 267793 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.8025. Min Act: -0.0000

Data Index: 848322 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.8844. Min Act: -0.0000

Data Index: 469243 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.8778. Min Act: -0.0000

Data Index: 250600 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.8725. Min Act: -0.0000

Data Index: 35448 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.8700. Min Act: -0.0000

Data Index: 87185 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.9671. Min Act: -0.0000

Data Index: 277132 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.6974. Min Act: -0.0000

Data Index: 181540 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.8297. Min Act: -0.0000

Data Index: 116977 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.7642. Min Act: -0.0000

Data Index: 576440 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 4.0177. Min Range: -4.0177

Max Act: 2.7407. Min Act: -0.0000

Data Index: 852591 (C4 (Web Text))

Max Activating Token Index: 811