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

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

Neuron 3726 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0817. Min Act: -0.0001

Data Index: 260041 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0710. Min Act: -0.0002

Data Index: 976126 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0689. Min Act: -0.0002

Data Index: 392483 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0656. Min Act: -0.0001

Data Index: 636415 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0654. Min Act: -0.0001

Data Index: 870325 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1213321 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1273602 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0643. Min Act: -0.0002

Data Index: 410328 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0674. Min Act: -0.0002

Data Index: 376771 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0591. Min Act: -0.0002

Data Index: 899738 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1044776 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0586. Min Act: -0.0002

Data Index: 851079 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0654. Min Act: -0.0002

Data Index: 127996 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0557. Min Act: -0.0002

Data Index: 739618 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0606. Min Act: -0.0002

Data Index: 814130 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0585. Min Act: -0.0002

Data Index: 976758 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0577. Min Act: -0.0002

Data Index: 57421 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0627. Min Act: -0.0001

Data Index: 304933 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0606. Min Act: -0.0002

Data Index: 829912 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0585. Min Act: -0.0001

Data Index: 216904 (C4 (Web Text))

Max Activating Token Index: 263