Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2296 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.3257. Min Act: -0.0001

Data Index: 20205 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.2960. Min Act: -0.0001

Data Index: 298333 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1548. Min Act: -0.0001

Data Index: 1069728 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1647. Min Act: -0.0001

Data Index: 57161 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.1509. Min Act: -0.0001

Data Index: 92245 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0618. Min Act: -0.0001

Data Index: 1227028 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0606. Min Act: -0.0001

Data Index: 372271 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0514. Min Act: -0.0001

Data Index: 1288845 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0359. Min Act: -0.0001

Data Index: 1197097 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9798. Min Act: -0.0001

Data Index: 1093906 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9413. Min Act: -0.0001

Data Index: 584548 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.3257. Min Range: -1.3257

Max Act: 1.0292. Min Act: -0.0001

Data Index: 970558 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9725. Min Act: -0.0001

Data Index: 550979 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9655. Min Act: -0.0001

Data Index: 1123398 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9621. Min Act: -0.0001

Data Index: 724830 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9587. Min Act: -0.0001

Data Index: 257921 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9539. Min Act: -0.0001

Data Index: 686001 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9819. Min Act: -0.0001

Data Index: 754475 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9541. Min Act: -0.0001

Data Index: 352298 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.3257. Min Range: -1.3257

Max Act: 0.9500. Min Act: -0.0001

Data Index: 798592 (C4 (Web Text))

Max Activating Token Index: 880