Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4031 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1797. Min Act: -0.0000

Data Index: 244398 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1363. Min Act: -0.0000

Data Index: 123606 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1053. Min Act: -0.0000

Data Index: 267416 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0681. Min Act: -0.0000

Data Index: 862286 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0424. Min Act: -0.0000

Data Index: 786636 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0656. Min Act: -0.0000

Data Index: 9835 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0669. Min Act: -0.0000

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0487. Min Act: -0.0000

Data Index: 150999 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0524. Min Act: -0.0000

Data Index: 40780 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0605. Min Act: -0.0000

Data Index: 750799 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1143566 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1099229 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0533. Min Act: -0.0000

Data Index: 262702 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0198. Min Act: -0.0000

Data Index: 133589 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0637. Min Act: -0.0000

Data Index: 823814 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1252316 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0507. Min Act: -0.0000

Data Index: 616376 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1268279 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0498. Min Act: -0.0000

Data Index: 110312 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1097151 (C4 (Web Text))

Max Activating Token Index: 148