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

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

Neuron 3229 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1211. Min Act: -0.0001

Data Index: 490927 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.2048. Min Act: -0.0001

Data Index: 263746 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0836. Min Act: -0.0001

Data Index: 707105 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0230. Min Act: -0.0001

Data Index: 28141 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0230. Min Act: -0.0001

Data Index: 1082338 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9899. Min Act: -0.0001

Data Index: 264045 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0555. Min Act: -0.0001

Data Index: 971935 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1073. Min Act: -0.0001

Data Index: 343048 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0138. Min Act: -0.0001

Data Index: 727785 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.0829. Min Act: -0.0001

Data Index: 674292 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8413. Min Act: -0.0001

Data Index: 1231093 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8911. Min Act: -0.0001

Data Index: 1002680 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9056. Min Act: -0.0001

Data Index: 1055988 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8772. Min Act: -0.0001

Data Index: 1315947 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9927. Min Act: -0.0001

Data Index: 342628 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9579. Min Act: -0.0001

Data Index: 1354929 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9814. Min Act: -0.0001

Data Index: 530969 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9843. Min Act: -0.0001

Data Index: 9397 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9978. Min Act: -0.0001

Data Index: 1166304 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9709. Min Act: -0.0001

Data Index: 305108 (C4 (Web Text))

Max Activating Token Index: 696