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

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

Neuron 4416 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: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0000

Data Index: 163703 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1105242 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0794. Min Act: -0.0000

Data Index: 691107 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1148054 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0916. Min Act: -0.0000

Data Index: 82508 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0784. Min Act: -0.0000

Data Index: 829103 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0720. Min Act: -0.0000

Data Index: 532860 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0707. Min Act: -0.0000

Data Index: 139703 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1009791 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1568818 (Python Code)

Max Activating Token Index: 429

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0600. Min Act: -0.0000

Data Index: 255360 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0636. Min Act: -0.0000

Data Index: 307442 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1114521 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1112035 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0662. Min Act: -0.0000

Data Index: 385304 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1224495 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0623. Min Act: -0.0000

Data Index: 1050455 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0581. Min Act: -0.0000

Data Index: 890363 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0644. Min Act: -0.0000

Data Index: 742867 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0628. Min Act: -0.0000

Data Index: 273272 (C4 (Web Text))

Max Activating Token Index: 497