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

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

Neuron 153 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.1493. Min Act: -0.0000

Data Index: 562764 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.3377. Min Act: -0.0000

Data Index: 781888 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.2021. Min Act: -0.0000

Data Index: 1237104 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.1988. Min Act: -0.0000

Data Index: 635889 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.2664. Min Act: -0.0000

Data Index: 73295 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.0931. Min Act: -0.0000

Data Index: 407570 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.1256. Min Act: -0.0000

Data Index: 924294 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1216419 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1050680 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.1625. Min Act: -0.0000

Data Index: 607733 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.1112. Min Act: -0.0000

Data Index: 939790 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.0794. Min Act: -0.0000

Data Index: 998898 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.3377. Min Range: -1.3377

Max Act: 0.9999. Min Act: -0.0000

Data Index: 749032 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.0611. Min Act: -0.0000

Data Index: 60118 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.0791. Min Act: -0.0000

Data Index: 980165 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.0280. Min Act: -0.0000

Data Index: 1103511 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.1612. Min Act: -0.0000

Data Index: 28745 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.1091. Min Act: -0.0000

Data Index: 1186668 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1233956 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.3377. Min Range: -1.3377

Max Act: 1.0793. Min Act: -0.0000

Data Index: 868547 (C4 (Web Text))

Max Activating Token Index: 584