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

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

Neuron 1217 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.7183. Min Act: -0.0000

Data Index: 1090699 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6444. Min Act: -0.0000

Data Index: 739614 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.0158. Min Act: -0.0000

Data Index: 307164 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.0893. Min Act: -0.0000

Data Index: 1226241 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.3907. Min Act: -0.0000

Data Index: 622841 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.1958. Min Act: -0.0000

Data Index: 1237315 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.7183. Min Range: -3.7183

Max Act: 2.9004. Min Act: -0.0000

Data Index: 424026 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.1685. Min Act: -0.0000

Data Index: 680219 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.0132. Min Act: -0.0000

Data Index: 1266002 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.2897. Min Act: -0.0000

Data Index: 578357 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.1420. Min Act: -0.0000

Data Index: 114201 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 3.7183. Min Range: -3.7183

Max Act: 2.8092. Min Act: -0.0000

Data Index: 1185185 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.0749. Min Act: -0.0000

Data Index: 162937 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.7183. Min Range: -3.7183

Max Act: 2.8962. Min Act: -0.0000

Data Index: 350357 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 3.7183. Min Range: -3.7183

Max Act: 2.8936. Min Act: -0.0000

Data Index: 139573 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 3.7183. Min Range: -3.7183

Max Act: 2.8852. Min Act: -0.0000

Data Index: 94357 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.0011. Min Act: -0.0000

Data Index: 806595 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 3.7183. Min Range: -3.7183

Max Act: 2.8208. Min Act: -0.0000

Data Index: 741428 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 3.7183. Min Range: -3.7183

Max Act: 2.9666. Min Act: -0.0000

Data Index: 789340 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 3.7183. Min Range: -3.7183

Max Act: 2.5325. Min Act: -0.0000

Data Index: 983763 (C4 (Web Text))

Max Activating Token Index: 664