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

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

Neuron 3239 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1331. Min Act: -0.0000

Data Index: 129750 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1115825 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1291409 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1012. Min Act: -0.0000

Data Index: 640980 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1003026 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1065082 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1344340 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0978. Min Act: -0.0000

Data Index: 458674 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0932. Min Act: -0.0000

Data Index: 240424 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0915. Min Act: -0.0000

Data Index: 780807 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0925. Min Act: -0.0000

Data Index: 483280 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1132902 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0941. Min Act: -0.0000

Data Index: 880127 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1096036 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1633691 (Python Code)

Max Activating Token Index: 154

Text #15

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0892. Min Act: -0.0000

Data Index: 549447 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0837. Min Act: -0.0000

Data Index: 456526 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0850. Min Act: -0.0000

Data Index: 154914 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1046296 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.1331. Min Range: -0.1331

Max Act: 0.0804. Min Act: -0.0000

Data Index: 762125 (C4 (Web Text))

Max Activating Token Index: 707