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

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

Neuron 5818 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.4635. Min Act: -0.0000

Data Index: 113443 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1026444 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.4989. Min Act: -0.0000

Data Index: 108930 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.4654. Min Act: -0.0000

Data Index: 809718 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3802. Min Act: -0.0000

Data Index: 62650 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3876. Min Act: -0.0000

Data Index: 737667 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1130416 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3619. Min Act: -0.0000

Data Index: 979193 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1056864 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1304900 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3045. Min Act: -0.0000

Data Index: 993275 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3662. Min Act: -0.0000

Data Index: 974695 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3595. Min Act: -0.0000

Data Index: 672709 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3667. Min Act: -0.0000

Data Index: 920837 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3393. Min Act: -0.0000

Data Index: 388918 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3105. Min Act: -0.0000

Data Index: 298065 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1069078 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3246. Min Act: -0.0000

Data Index: 955648 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3207. Min Act: -0.0000

Data Index: 902007 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.4989. Min Range: -0.4989

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1079608 (C4 (Web Text))

Max Activating Token Index: 705