Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 709 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.5661. Min Act: -0.0000

Data Index: 151646 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.4381. Min Act: -0.0001

Data Index: 875540 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.3906. Min Act: -0.0000

Data Index: 828251 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.2563. Min Act: -0.0000

Data Index: 712481 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1847. Min Act: -0.0000

Data Index: 700930 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1441. Min Act: -0.0000

Data Index: 560196 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.1265. Min Act: -0.0000

Data Index: 594397 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0584. Min Act: -0.0000

Data Index: 300830 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0771. Min Act: -0.0000

Data Index: 293867 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0585. Min Act: -0.0000

Data Index: 981499 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0567. Min Act: -0.0000

Data Index: 357568 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1212837 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0371. Min Act: -0.0001

Data Index: 449262 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1333511 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9953. Min Act: -0.0000

Data Index: 692902 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1012052 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.5661. Min Range: -1.5661

Max Act: 1.0403. Min Act: -0.0001

Data Index: 27630 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9977. Min Act: -0.0000

Data Index: 997551 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9912. Min Act: -0.0000

Data Index: 993114 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.5661. Min Range: -1.5661

Max Act: 0.9861. Min Act: -0.0001

Data Index: 135677 (C4 (Web Text))

Max Activating Token Index: 728