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

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

Neuron 315 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6104. Min Range: -6.6104

Max Act: 6.6104. Min Act: -0.0000

Data Index: 1002935 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 6.6104. Min Range: -6.6104

Max Act: 6.4138. Min Act: -0.0000

Data Index: 1250514 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.9564. Min Act: -0.0000

Data Index: 1026999 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 6.6104. Min Range: -6.6104

Max Act: 6.0282. Min Act: -0.0000

Data Index: 1175839 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.8934. Min Act: -0.0000

Data Index: 558392 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.5208. Min Act: -0.0000

Data Index: 1242045 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.5583. Min Act: -0.0000

Data Index: 315906 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.6809. Min Act: -0.0000

Data Index: 82493 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.6671. Min Act: -0.0000

Data Index: 1245591 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.4929. Min Act: -0.0000

Data Index: 206638 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.4278. Min Act: -0.0000

Data Index: 767440 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.4093. Min Act: -0.0000

Data Index: 665305 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.2389. Min Act: -0.0000

Data Index: 338514 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.3310. Min Act: -0.0000

Data Index: 946337 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.2550. Min Act: -0.0000

Data Index: 1338662 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.0823. Min Act: -0.0000

Data Index: 70303 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.0811. Min Act: -0.0000

Data Index: 522587 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.2531. Min Act: -0.0000

Data Index: 1290635 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 6.6104. Min Range: -6.6104

Max Act: 4.8403. Min Act: -0.0000

Data Index: 386862 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 6.6104. Min Range: -6.6104

Max Act: 5.1838. Min Act: -0.0000

Data Index: 903177 (C4 (Web Text))

Max Activating Token Index: 419