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

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

Neuron 1931 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0002

Data Index: 841149 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0673. Min Act: -0.0002

Data Index: 213558 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0733. Min Act: -0.0002

Data Index: 444442 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1109990 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0716. Min Act: -0.0002

Data Index: 63158 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1288313 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0654. Min Act: -0.0002

Data Index: 298332 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0681. Min Act: -0.0002

Data Index: 14049 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0702. Min Act: -0.0002

Data Index: 972714 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1169982 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1318755 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1220912 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0664. Min Act: -0.0002

Data Index: 964061 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0669. Min Act: -0.0002

Data Index: 650368 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0686. Min Act: -0.0002

Data Index: 506418 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0657. Min Act: -0.0002

Data Index: 367808 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0700. Min Act: -0.0002

Data Index: 950397 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0726. Min Act: -0.0002

Data Index: 642110 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0701. Min Act: -0.0002

Data Index: 537774 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0707. Min Act: -0.0002

Data Index: 37654 (C4 (Web Text))

Max Activating Token Index: 356