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

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

Neuron 4953 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.5512. Min Act: -0.0000

Data Index: 896496 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1106880 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.3512. Min Act: -0.0000

Data Index: 985725 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.3196. Min Act: -0.0000

Data Index: 808528 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.3588. Min Act: -0.0000

Data Index: 521011 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2928. Min Act: -0.0000

Data Index: 534499 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2737. Min Act: -0.0000

Data Index: 299316 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.3126. Min Act: -0.0000

Data Index: 76716 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.3105. Min Act: -0.0000

Data Index: 734059 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.3355. Min Act: -0.0000

Data Index: 42536 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2730. Min Act: -0.0000

Data Index: 478106 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1074888 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2888. Min Act: -0.0000

Data Index: 374743 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1117623 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2916. Min Act: -0.0000

Data Index: 102051 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1287949 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.3102. Min Act: -0.0000

Data Index: 52505 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.3238. Min Act: -0.0000

Data Index: 458233 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2731. Min Act: -0.0000

Data Index: 41078 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.5512. Min Range: -0.5512

Max Act: 0.2895. Min Act: -0.0000

Data Index: 290653 (C4 (Web Text))

Max Activating Token Index: 263