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

Dataset: The Pile

Neuron 929 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1183284 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.9540. Min Act: -0.0000

Data Index: 461635 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.9454. Min Act: -0.0000

Data Index: 425571 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1551266 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.8346. Min Act: -0.0000

Data Index: 84246 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1899516 (The Pile)

Max Activating Token Index: 772

Text #6

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.9071. Min Act: -0.0000

Data Index: 467720 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1414876 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1318402 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.8354. Min Act: -0.0000

Data Index: 166039 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.8606. Min Act: -0.0000

Data Index: 457669 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7706. Min Act: -0.0000

Data Index: 652280 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1033017 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1372107 (The Pile)

Max Activating Token Index: 241

Text #14

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7680. Min Act: -0.0000

Data Index: 466161 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1173678 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1226126 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7304. Min Act: -0.0000

Data Index: 329626 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7684. Min Act: -0.0000

Data Index: 743560 (The Pile)

Max Activating Token Index: 129

Text #19

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1576908 (The Pile)

Max Activating Token Index: 478