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

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

Neuron 2788 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: 1.3088. Min Range: -1.3088

Max Act: 1.3088. Min Act: -0.0000

Data Index: 880385 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.2499. Min Act: -0.0000

Data Index: 513024 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1248342 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1456. Min Act: -0.0000

Data Index: 994868 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.2968. Min Act: -0.0000

Data Index: 883498 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1053181 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1536076 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0797. Min Act: -0.0000

Data Index: 1247710 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0887. Min Act: -0.0000

Data Index: 780500 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1133340 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1063032 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1126000 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0637. Min Act: -0.0000

Data Index: 813964 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1087024 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1648991 (Python Code)

Max Activating Token Index: 923

Text #15

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0714. Min Act: -0.0000

Data Index: 878192 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.3088. Min Range: -1.3088

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1521598 (Python Code)

Max Activating Token Index: 903

Text #17

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0343. Min Act: -0.0000

Data Index: 7215 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0314. Min Act: -0.0000

Data Index: 402965 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.3088. Min Range: -1.3088

Max Act: 1.0144. Min Act: -0.0000

Data Index: 195201 (C4 (Web Text))

Max Activating Token Index: 296