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

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

Neuron 562 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.6543. Min Act: -0.0000

Data Index: 306844 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1239653 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.6122. Min Act: -0.0000

Data Index: 588751 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.6015. Min Act: -0.0000

Data Index: 741383 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1301885 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5590. Min Act: -0.0000

Data Index: 123457 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5607. Min Act: -0.0000

Data Index: 894742 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1086643 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5479. Min Act: -0.0000

Data Index: 44259 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5564. Min Act: -0.0000

Data Index: 521969 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1090308 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1041466 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5129. Min Act: -0.0000

Data Index: 396342 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5398. Min Act: -0.0000

Data Index: 738501 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1100272 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5113. Min Act: -0.0000

Data Index: 611024 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1124393 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4952. Min Act: -0.0000

Data Index: 682158 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.5178. Min Act: -0.0000

Data Index: 77509 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.6543. Min Range: -0.6543

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1018405 (C4 (Web Text))

Max Activating Token Index: 68