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

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

Neuron 3512 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.9638. Min Act: -0.0000

Data Index: 601228 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1504075 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1610438 (Python Code)

Max Activating Token Index: 489

Text #3

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.9165. Min Act: -0.0000

Data Index: 310467 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1629271 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8195. Min Act: -0.0000

Data Index: 639616 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7828. Min Act: -0.0000

Data Index: 340937 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8673. Min Act: -0.0000

Data Index: 754291 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7551. Min Act: -0.0000

Data Index: 155366 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7468. Min Act: -0.0000

Data Index: 207489 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7802. Min Act: -0.0000

Data Index: 741348 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8074. Min Act: -0.0000

Data Index: 681403 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.8160. Min Act: -0.0000

Data Index: 225007 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7680. Min Act: -0.0000

Data Index: 127234 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7849. Min Act: -0.0000

Data Index: 1456754 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1583461 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7457. Min Act: -0.0000

Data Index: 872073 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7259. Min Act: -0.0000

Data Index: 780305 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.7309. Min Act: -0.0000

Data Index: 943292 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.9638. Min Range: -0.9638

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1274431 (C4 (Web Text))

Max Activating Token Index: 766