Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1946 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0926. Min Act: -0.0000

Data Index: 2523 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0912. Min Act: -0.0000

Data Index: 647263 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0880. Min Act: -0.0000

Data Index: 52896 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1488057 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1640980 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1340234 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0769. Min Act: -0.0000

Data Index: 148078 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0789. Min Act: 0.0000

Data Index: 1304386 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1433553 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1124196 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0746. Min Act: -0.0000

Data Index: 358285 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1124028 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0728. Min Act: -0.0000

Data Index: 232422 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0727. Min Act: -0.0000

Data Index: 932116 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0763. Min Act: -0.0000

Data Index: 519614 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1550992 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0763. Min Act: -0.0000

Data Index: 214482 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0710. Min Act: -0.0000

Data Index: 470948 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0761. Min Act: -0.0000

Data Index: 326011 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0719. Min Act: -0.0000

Data Index: 516451 (C4 (Web Text))

Max Activating Token Index: 528