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

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

Neuron 1641 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: 4.5837. Min Range: -4.5837

Max Act: 4.5837. Min Act: -0.0000

Data Index: 492524 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.0008. Min Act: -0.0000

Data Index: 958249 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.9297. Min Act: -0.0000

Data Index: 1162716 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.8959. Min Act: -0.0000

Data Index: 917653 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.6274. Min Act: -0.0000

Data Index: 487101 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.7927. Min Act: -0.0000

Data Index: 318458 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.6321. Min Act: -0.0000

Data Index: 11774 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.6030. Min Act: -0.0000

Data Index: 305336 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.7725. Min Act: -0.0000

Data Index: 1308043 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.5442. Min Act: -0.0000

Data Index: 188472 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.5685. Min Act: -0.0000

Data Index: 719451 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.4977. Min Act: -0.0000

Data Index: 182495 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.6667. Min Act: -0.0000

Data Index: 1320596 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.4953. Min Act: -0.0000

Data Index: 357675 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.6093. Min Act: -0.0000

Data Index: 779805 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.4693. Min Act: -0.0000

Data Index: 630388 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.4094. Min Act: -0.0000

Data Index: 446657 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.5974. Min Act: -0.0000

Data Index: 1219036 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.4058. Min Act: -0.0000

Data Index: 40594 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 4.5837. Min Range: -4.5837

Max Act: 3.3718. Min Act: -0.0000

Data Index: 227715 (C4 (Web Text))

Max Activating Token Index: 922