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

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

Neuron 1208 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.5997. Min Act: -0.0001

Data Index: 158329 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.3666. Min Act: -0.0000

Data Index: 271721 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2749. Min Act: -0.0000

Data Index: 291816 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.3164. Min Act: -0.0000

Data Index: 434281 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2729. Min Act: -0.0001

Data Index: 706349 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2580. Min Act: -0.0001

Data Index: 547137 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2146. Min Act: -0.0001

Data Index: 151369 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2366. Min Act: -0.0001

Data Index: 1142184 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2654. Min Act: -0.0000

Data Index: 870551 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2183. Min Act: -0.0001

Data Index: 175544 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.1849. Min Act: -0.0000

Data Index: 393311 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.1860. Min Act: -0.0001

Data Index: 439654 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.1548. Min Act: -0.0000

Data Index: 403182 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.0927. Min Act: -0.0000

Data Index: 20995 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.0837. Min Act: -0.0001

Data Index: 182167 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.1687. Min Act: -0.0001

Data Index: 820726 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.2386. Min Act: -0.0001

Data Index: 1082973 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.1581. Min Act: -0.0001

Data Index: 1596706 (Python Code)

Max Activating Token Index: 402

Text #18

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.0957. Min Act: -0.0001

Data Index: 404957 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 1.5997. Min Range: -1.5997

Max Act: 1.0585. Min Act: -0.0000

Data Index: 827463 (C4 (Web Text))

Max Activating Token Index: 367