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

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

Neuron 2569 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: 1.4305. Min Range: -1.4305

Max Act: 1.4305. Min Act: -0.0000

Data Index: 992971 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2458. Min Act: -0.0000

Data Index: 910924 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2616. Min Act: -0.0000

Data Index: 664885 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2111. Min Act: -0.0000

Data Index: 324389 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1877. Min Act: -0.0000

Data Index: 660039 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1202934 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1538. Min Act: -0.0000

Data Index: 170386 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1092221 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1197. Min Act: -0.0000

Data Index: 442181 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1095834 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0662. Min Act: -0.0000

Data Index: 385375 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1379805 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0470. Min Act: -0.0000

Data Index: 785034 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1090. Min Act: -0.0000

Data Index: 453198 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1349694 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0102. Min Act: -0.0000

Data Index: 1321925 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0557. Min Act: -0.0000

Data Index: 920539 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1247334 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1109014 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0077. Min Act: -0.0000

Data Index: 204409 (C4 (Web Text))

Max Activating Token Index: 211