Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2920 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0001

Data Index: 718056 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1467067 (Python Code)

Max Activating Token Index: 603

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1104588 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0876. Min Act: -0.0001

Data Index: 719598 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0877. Min Act: -0.0001

Data Index: 135456 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1433593 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1287918 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0819. Min Act: -0.0001

Data Index: 217332 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0818. Min Act: -0.0001

Data Index: 718548 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0812. Min Act: -0.0001

Data Index: 237903 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1509878 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0784. Min Act: -0.0001

Data Index: 708442 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0781. Min Act: -0.0001

Data Index: 219764 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1383265 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1139676 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1608896 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0756. Min Act: -0.0001

Data Index: 459287 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1646395 (Python Code)

Max Activating Token Index: 989

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0728. Min Act: -0.0001

Data Index: 205220 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0702. Min Act: -0.0001

Data Index: 953182 (C4 (Web Text))

Max Activating Token Index: 759