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

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

Neuron 4610 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.9226. Min Act: -0.0000

Data Index: 605058 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.7092. Min Act: -0.0000

Data Index: 835834 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6970. Min Act: -0.0000

Data Index: 707975 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6349. Min Act: -0.0000

Data Index: 505025 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.7438. Min Act: -0.0000

Data Index: 136116 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5925. Min Act: -0.0000

Data Index: 158607 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.8023. Min Act: -0.0000

Data Index: 32296 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6752. Min Act: -0.0000

Data Index: 44525 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6584. Min Act: -0.0000

Data Index: 950817 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6575. Min Act: -0.0000

Data Index: 969659 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6691. Min Act: -0.0000

Data Index: 184371 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6613. Min Act: -0.0000

Data Index: 1158144 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.4639. Min Act: -0.0000

Data Index: 923288 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5485. Min Act: -0.0000

Data Index: 50615 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.6201. Min Act: -0.0000

Data Index: 556699 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5732. Min Act: -0.0000

Data Index: 610510 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5342. Min Act: -0.0000

Data Index: 12685 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.7027. Min Act: -0.0000

Data Index: 195179 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5422. Min Act: -0.0000

Data Index: 75723 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.9226. Min Range: -1.9226

Max Act: 1.5737. Min Act: -0.0000

Data Index: 1313675 (C4 (Web Text))

Max Activating Token Index: 999