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

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

Neuron 6140 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0162. Min Range: -5.0162

Max Act: 5.0162. Min Act: -0.0001

Data Index: 279623 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 5.0162. Min Range: -5.0162

Max Act: 4.4247. Min Act: -0.0001

Data Index: 192180 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 5.0162. Min Range: -5.0162

Max Act: 4.6054. Min Act: -0.0001

Data Index: 1292365 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 5.0162. Min Range: -5.0162

Max Act: 4.4618. Min Act: -0.0001

Data Index: 695807 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 5.0162. Min Range: -5.0162

Max Act: 4.1759. Min Act: -0.0001

Data Index: 1152889 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.9663. Min Act: -0.0001

Data Index: 410177 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.9623. Min Act: -0.0000

Data Index: 513740 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.7655. Min Act: -0.0001

Data Index: 1184 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.9021. Min Act: -0.0001

Data Index: 896511 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.8527. Min Act: -0.0001

Data Index: 1282856 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.7808. Min Act: -0.0001

Data Index: 11553 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.9359. Min Act: -0.0001

Data Index: 716454 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.7584. Min Act: -0.0001

Data Index: 503560 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.7623. Min Act: -0.0001

Data Index: 851970 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.7497. Min Act: -0.0001

Data Index: 930337 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.7389. Min Act: -0.0001

Data Index: 693698 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.5459. Min Act: -0.0001

Data Index: 170020 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.8329. Min Act: -0.0001

Data Index: 1047793 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.8715. Min Act: -0.0001

Data Index: 147294 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 5.0162. Min Range: -5.0162

Max Act: 3.6609. Min Act: -0.0001

Data Index: 600777 (C4 (Web Text))

Max Activating Token Index: 671