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

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

Neuron 2622 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1566231 (Python Code)

Max Activating Token Index: 438

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1583228 (Python Code)

Max Activating Token Index: 211

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0464. Min Act: -0.0002

Data Index: 801562 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: -0.0002

Data Index: 227909 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1072624 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1488364 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1652538 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1616975 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1210979 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0477. Min Act: -0.0002

Data Index: 414845 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1199620 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1068866 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1588972 (Python Code)

Max Activating Token Index: 638

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0480. Min Act: -0.0002

Data Index: 48898 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1230268 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1423441 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1540959 (Python Code)

Max Activating Token Index: 772

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1498759 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1564536 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1553939 (Python Code)

Max Activating Token Index: 712