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

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

Neuron 1563 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: 0.9192. Min Range: -0.9192

Max Act: 0.9192. Min Act: -0.0001

Data Index: 960635 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8942. Min Act: -0.0001

Data Index: 1093502 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8734. Min Act: -0.0001

Data Index: 590573 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8646. Min Act: -0.0001

Data Index: 17408 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8582. Min Act: -0.0001

Data Index: 328923 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8385. Min Act: -0.0001

Data Index: 670549 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8244. Min Act: -0.0001

Data Index: 136170 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8888. Min Act: -0.0001

Data Index: 759390 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8196. Min Act: -0.0001

Data Index: 284055 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7906. Min Act: -0.0001

Data Index: 819786 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8085. Min Act: -0.0001

Data Index: 1183562 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7981. Min Act: -0.0001

Data Index: 860655 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8010. Min Act: -0.0001

Data Index: 762033 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7576. Min Act: -0.0001

Data Index: 540801 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.8376. Min Act: -0.0001

Data Index: 484273 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7917. Min Act: -0.0001

Data Index: 775044 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7608. Min Act: -0.0001

Data Index: 898075 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7898. Min Act: -0.0001

Data Index: 418687 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7540. Min Act: -0.0001

Data Index: 1314358 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.9192. Min Range: -0.9192

Max Act: 0.7783. Min Act: -0.0001

Data Index: 1349735 (C4 (Web Text))

Max Activating Token Index: 280