Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5332 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.7641. Min Range: -5.7641

Max Act: 5.7641. Min Act: -0.0000

Data Index: 1326913 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 5.7641. Min Range: -5.7641

Max Act: 5.1071. Min Act: -0.0000

Data Index: 217403 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 5.7641. Min Range: -5.7641

Max Act: 4.7111. Min Act: -0.0000

Data Index: 251485 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 5.7641. Min Range: -5.7641

Max Act: 4.6092. Min Act: -0.0000

Data Index: 314339 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 5.7641. Min Range: -5.7641

Max Act: 4.0776. Min Act: -0.0000

Data Index: 460938 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 5.7641. Min Range: -5.7641

Max Act: 4.0431. Min Act: -0.0000

Data Index: 551743 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.9834. Min Act: -0.0000

Data Index: 1108132 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.9888. Min Act: -0.0000

Data Index: 883903 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.9737. Min Act: -0.0000

Data Index: 1030939 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.9629. Min Act: -0.0000

Data Index: 1223749 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.8976. Min Act: -0.0000

Data Index: 978495 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 5.7641. Min Range: -5.7641

Max Act: 4.0301. Min Act: -0.0000

Data Index: 884969 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.8120. Min Act: -0.0000

Data Index: 628563 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.7914. Min Act: -0.0000

Data Index: 1319296 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.9327. Min Act: -0.0000

Data Index: 681271 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.7640. Min Act: -0.0000

Data Index: 304656 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.5649. Min Act: -0.0000

Data Index: 1066617 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.8760. Min Act: -0.0000

Data Index: 1325991 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.8760. Min Act: -0.0000

Data Index: 721924 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 5.7641. Min Range: -5.7641

Max Act: 3.8562. Min Act: -0.0000

Data Index: 649045 (C4 (Web Text))

Max Activating Token Index: 127