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

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

Neuron 965 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: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0002

Data Index: 991420 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0899. Min Act: -0.0002

Data Index: 948615 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0941. Min Act: -0.0002

Data Index: 658157 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0917. Min Act: -0.0002

Data Index: 884934 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0876. Min Act: -0.0002

Data Index: 650095 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0917. Min Act: -0.0002

Data Index: 660977 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0832. Min Act: -0.0002

Data Index: 637526 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1236369 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0879. Min Act: -0.0002

Data Index: 197560 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0874. Min Act: -0.0002

Data Index: 43710 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1257725 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0900. Min Act: -0.0002

Data Index: 516720 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0896. Min Act: -0.0002

Data Index: 352261 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1608794 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0863. Min Act: -0.0002

Data Index: 788337 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1091371 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0901. Min Act: -0.0002

Data Index: 772700 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0861. Min Act: -0.0002

Data Index: 957094 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0891. Min Act: -0.0002

Data Index: 566461 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0890. Min Act: -0.0002

Data Index: 50671 (C4 (Web Text))

Max Activating Token Index: 534