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

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

Neuron 1166 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0000

Data Index: 460213 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1646940 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1439336 (Python Code)

Max Activating Token Index: 1013

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1567351 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1405086 (Python Code)

Max Activating Token Index: 809

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1543535 (Python Code)

Max Activating Token Index: 840

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1439511 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1410918 (Python Code)

Max Activating Token Index: 805

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1596590 (Python Code)

Max Activating Token Index: 749

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1529456 (Python Code)

Max Activating Token Index: 711

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1526116 (Python Code)

Max Activating Token Index: 652

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1594823 (Python Code)

Max Activating Token Index: 880

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1449220 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0645. Min Act: -0.0000

Data Index: 261981 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1579122 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1478365 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1529443 (Python Code)

Max Activating Token Index: 797

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0615. Min Act: -0.0000

Data Index: 969728 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1219902 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1478513 (Python Code)

Max Activating Token Index: 898