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

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

Neuron 4817 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: 2.7879. Min Range: -2.7879

Max Act: 2.7879. Min Act: -0.0000

Data Index: 1201049 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.6530. Min Act: -0.0000

Data Index: 938851 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.3602. Min Act: -0.0000

Data Index: 943726 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.3534. Min Act: -0.0000

Data Index: 1173180 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.4180. Min Act: -0.0000

Data Index: 588343 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.2421. Min Act: -0.0000

Data Index: 661790 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.1990. Min Act: -0.0000

Data Index: 1208716 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.2940. Min Act: -0.0000

Data Index: 826189 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.2291. Min Act: -0.0000

Data Index: 10930 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 2.7879. Min Range: -2.7879

Max Act: 1.9852. Min Act: -0.0000

Data Index: 54420 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.0852. Min Act: -0.0000

Data Index: 939602 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 2.7879. Min Range: -2.7879

Max Act: 1.9611. Min Act: -0.0000

Data Index: 312819 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 2.7879. Min Range: -2.7879

Max Act: 1.9542. Min Act: -0.0000

Data Index: 1161600 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 2.7879. Min Range: -2.7879

Max Act: 2.0340. Min Act: -0.0000

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 2.7879. Min Range: -2.7879

Max Act: 1.8224. Min Act: -0.0000

Data Index: 457712 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 2.7879. Min Range: -2.7879

Max Act: 1.8282. Min Act: -0.0000

Data Index: 980263 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 2.7879. Min Range: -2.7879

Max Act: 1.9851. Min Act: -0.0000

Data Index: 118738 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 2.7879. Min Range: -2.7879

Max Act: 1.8811. Min Act: -0.0000

Data Index: 1251761 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 2.7879. Min Range: -2.7879

Max Act: 1.8739. Min Act: -0.0000

Data Index: 771693 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 2.7879. Min Range: -2.7879

Max Act: 1.7053. Min Act: -0.0000

Data Index: 1013903 (C4 (Web Text))

Max Activating Token Index: 902