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

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

Neuron 1732 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.8641. Min Act: -0.0000

Data Index: 1313778 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.2949. Min Act: -0.0000

Data Index: 862384 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.3962. Min Act: -0.0000

Data Index: 88256 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.9832. Min Act: -0.0000

Data Index: 727662 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.0858. Min Act: -0.0000

Data Index: 1229753 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 2.8641. Min Range: -2.8641

Max Act: 2.0058. Min Act: -0.0000

Data Index: 1187701 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1349834 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.6846. Min Act: -0.0000

Data Index: 1027953 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.7633. Min Act: -0.0000

Data Index: 36751 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.6924. Min Act: -0.0000

Data Index: 799709 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.6508. Min Act: -0.0000

Data Index: 614094 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.4965. Min Act: -0.0000

Data Index: 374089 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.5974. Min Act: -0.0000

Data Index: 1511132 (Python Code)

Max Activating Token Index: 652

Text #13

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.6361. Min Act: -0.0000

Data Index: 1289267 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.5165. Min Act: -0.0000

Data Index: 1323239 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.4488. Min Act: -0.0000

Data Index: 852000 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.4451. Min Act: -0.0000

Data Index: 1131165 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.4795. Min Act: -0.0000

Data Index: 1102301 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.4360. Min Act: -0.0000

Data Index: 355473 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 2.8641. Min Range: -2.8641

Max Act: 1.4482. Min Act: -0.0000

Data Index: 977504 (C4 (Web Text))

Max Activating Token Index: 573