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

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

Neuron 852 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2980. Min Act: -0.0001

Data Index: 603096 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2368. Min Act: -0.0000

Data Index: 137188 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2258. Min Act: -0.0001

Data Index: 359958 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2192. Min Act: -0.0001

Data Index: 454347 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1311343 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1237481 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2083. Min Act: -0.0001

Data Index: 1053882 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1912. Min Act: -0.0000

Data Index: 271762 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1888. Min Act: -0.0000

Data Index: 566086 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1849. Min Act: -0.0000

Data Index: 785676 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1812. Min Act: -0.0001

Data Index: 84501 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1271463 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1720. Min Act: -0.0001

Data Index: 890374 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1787. Min Act: -0.0001

Data Index: 458819 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1764. Min Act: -0.0001

Data Index: 545693 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1633. Min Act: -0.0001

Data Index: 467767 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1231428 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1148639 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1713. Min Act: -0.0000

Data Index: 122840 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1024139 (C4 (Web Text))

Max Activating Token Index: 175