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

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

Neuron 2135 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1591128 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1396659 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0767. Min Act: -0.0001

Data Index: 922819 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0713. Min Act: -0.0001

Data Index: 133435 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1548261 (Python Code)

Max Activating Token Index: 234

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0688. Min Act: -0.0001

Data Index: 402205 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0769. Min Act: -0.0001

Data Index: 885531 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1189745 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0726. Min Act: -0.0001

Data Index: 882085 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0734. Min Act: -0.0001

Data Index: 137249 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1376011 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1467879 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1509352 (Python Code)

Max Activating Token Index: 691

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0660. Min Act: -0.0001

Data Index: 46198 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0682. Min Act: -0.0001

Data Index: 430979 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0733. Min Act: -0.0001

Data Index: 343286 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0702. Min Act: -0.0001

Data Index: 429874 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1260073 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0737. Min Act: -0.0001

Data Index: 356331 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0697. Min Act: -0.0001

Data Index: 583578 (C4 (Web Text))

Max Activating Token Index: 215