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

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

Neuron 2605 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: 4.5751. Min Range: -4.5751

Max Act: 4.5751. Min Act: -0.0000

Data Index: 72489 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 4.5751. Min Range: -4.5751

Max Act: 4.0010. Min Act: -0.0000

Data Index: 134466 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 4.5751. Min Range: -4.5751

Max Act: 4.1041. Min Act: -0.0000

Data Index: 1286877 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.7100. Min Act: -0.0000

Data Index: 260718 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.5773. Min Act: -0.0000

Data Index: 1168046 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.4945. Min Act: -0.0000

Data Index: 491101 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.4822. Min Act: -0.0000

Data Index: 1200850 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.4964. Min Act: -0.0000

Data Index: 676268 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.4630. Min Act: -0.0000

Data Index: 1329774 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.4067. Min Act: -0.0000

Data Index: 1022147 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.1820. Min Act: -0.0000

Data Index: 761744 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.1104. Min Act: -0.0000

Data Index: 160554 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.0642. Min Act: -0.0000

Data Index: 711030 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 4.5751. Min Range: -4.5751

Max Act: 2.8724. Min Act: -0.0000

Data Index: 508550 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 4.5751. Min Range: -4.5751

Max Act: 3.0130. Min Act: -0.0000

Data Index: 847386 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 4.5751. Min Range: -4.5751

Max Act: 2.9898. Min Act: -0.0000

Data Index: 450216 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 4.5751. Min Range: -4.5751

Max Act: 2.9513. Min Act: -0.0000

Data Index: 87779 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 4.5751. Min Range: -4.5751

Max Act: 2.9114. Min Act: -0.0000

Data Index: 644888 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 4.5751. Min Range: -4.5751

Max Act: 2.8328. Min Act: -0.0000

Data Index: 29932 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 4.5751. Min Range: -4.5751

Max Act: 2.5950. Min Act: -0.0000

Data Index: 651058 (C4 (Web Text))

Max Activating Token Index: 114