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

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

Neuron 4644 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.3272. Min Act: -0.0003

Data Index: 837074 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.1090. Min Act: -0.0003

Data Index: 118819 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0382. Min Act: -0.0003

Data Index: 119666 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0108. Min Act: -0.0003

Data Index: 380295 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9794. Min Act: -0.0002

Data Index: 627709 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0271. Min Act: -0.0002

Data Index: 114668 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0503. Min Act: -0.0003

Data Index: 58380 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0430. Min Act: -0.0002

Data Index: 984680 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.3272. Min Range: -1.3272

Max Act: 1.0030. Min Act: -0.0002

Data Index: 765551 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9752. Min Act: -0.0002

Data Index: 1239270 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9894. Min Act: -0.0003

Data Index: 1076684 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9687. Min Act: -0.0002

Data Index: 666453 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9682. Min Act: -0.0002

Data Index: 1120745 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9362. Min Act: -0.0003

Data Index: 103057 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9509. Min Act: -0.0002

Data Index: 1195575 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9683. Min Act: -0.0003

Data Index: 42359 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9903. Min Act: -0.0002

Data Index: 420360 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9771. Min Act: -0.0003

Data Index: 1131746 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.8949. Min Act: -0.0002

Data Index: 177720 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 1.3272. Min Range: -1.3272

Max Act: 0.9494. Min Act: -0.0002

Data Index: 1160987 (C4 (Web Text))

Max Activating Token Index: 197