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

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

Neuron 5392 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.5915. Min Act: -0.0000

Data Index: 460003 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.4453. Min Act: -0.0000

Data Index: 1096677 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.3298. Min Act: -0.0000

Data Index: 832063 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.4281. Min Act: -0.0000

Data Index: 608811 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1574. Min Act: -0.0000

Data Index: 698297 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1291648 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.2795. Min Act: -0.0000

Data Index: 601792 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1368. Min Act: -0.0000

Data Index: 752989 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1745. Min Act: -0.0000

Data Index: 1293139 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1287308 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1075327 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1000506 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1821. Min Act: -0.0000

Data Index: 464555 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1141456 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1481. Min Act: -0.0000

Data Index: 27347 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1528. Min Act: -0.0000

Data Index: 179612 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1290. Min Act: -0.0000

Data Index: 872371 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.5915. Min Range: -1.5915

Max Act: 0.9934. Min Act: -0.0000

Data Index: 334578 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.0805. Min Act: -0.0000

Data Index: 582528 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1110. Min Act: -0.0000

Data Index: 579048 (C4 (Web Text))

Max Activating Token Index: 158