Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1925 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6946. Min Act: -0.0001

Data Index: 1197176 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.7188. Min Act: -0.0001

Data Index: 677743 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.5609. Min Act: -0.0001

Data Index: 1266641 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.4110. Min Act: -0.0001

Data Index: 128308 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.3573. Min Act: -0.0001

Data Index: 213238 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.5679. Min Act: -0.0001

Data Index: 852759 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.4466. Min Act: -0.0001

Data Index: 160941 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.3486. Min Act: -0.0001

Data Index: 1387686 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.2946. Min Act: -0.0001

Data Index: 1269159 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.3724. Min Act: -0.0001

Data Index: 1219956 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.3568. Min Act: -0.0001

Data Index: 545176 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.2445. Min Act: -0.0001

Data Index: 392570 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.2902. Min Act: -0.0001

Data Index: 726088 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.3249. Min Act: -0.0001

Data Index: 1006367 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.4126. Min Act: -0.0001

Data Index: 1112385 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.2918. Min Act: -0.0001

Data Index: 306 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.3045. Min Act: -0.0001

Data Index: 35147 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.2921. Min Act: -0.0001

Data Index: 672187 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.2191. Min Act: -0.0001

Data Index: 1280708 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.2650. Min Act: -0.0001

Data Index: 854082 (C4 (Web Text))

Max Activating Token Index: 251