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

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

Neuron 37 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.6594. Min Act: -0.0000

Data Index: 302345 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.3923. Min Act: -0.0000

Data Index: 1274657 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.5649. Min Act: -0.0000

Data Index: 486247 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0432. Min Act: -0.0000

Data Index: 678726 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.9937. Min Act: -0.0000

Data Index: 3673 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0613. Min Act: -0.0000

Data Index: 434679 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.9566. Min Act: -0.0000

Data Index: 76823 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0600. Min Act: -0.0000

Data Index: 151489 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.7893. Min Act: -0.0000

Data Index: 127159 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 2.6594. Min Range: -2.6594

Max Act: 2.0099. Min Act: -0.0000

Data Index: 387672 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.8472. Min Act: -0.0000

Data Index: 824104 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.9668. Min Act: -0.0000

Data Index: 938432 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.6810. Min Act: -0.0000

Data Index: 90592 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.6648. Min Act: -0.0000

Data Index: 637042 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.5730. Min Act: -0.0000

Data Index: 1327017 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.5099. Min Act: -0.0000

Data Index: 1106032 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.5446. Min Act: 0.0000

Data Index: 891844 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.5624. Min Act: -0.0000

Data Index: 987012 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.4289. Min Act: -0.0000

Data Index: 787507 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 2.6594. Min Range: -2.6594

Max Act: 1.3783. Min Act: -0.0000

Data Index: 465254 (C4 (Web Text))

Max Activating Token Index: 212