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

Dataset: The Pile

Neuron 3360 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1176969 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.9131. Min Act: -0.0000

Data Index: 983019 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.9504. Min Act: -0.0000

Data Index: 466593 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1944760 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8419. Min Act: -0.0000

Data Index: 762005 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8913. Min Act: -0.0000

Data Index: 989529 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7632. Min Act: -0.0000

Data Index: 620626 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1806878 (The Pile)

Max Activating Token Index: 313

Text #8

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1875140 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1780659 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6942. Min Act: -0.0000

Data Index: 252991 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1590496 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1821518 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6844. Min Act: -0.0000

Data Index: 778962 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.7168. Min Act: -0.0000

Data Index: 695319 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1678965 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6490. Min Act: -0.0000

Data Index: 55676 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6384. Min Act: -0.0000

Data Index: 322027 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1744672 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 0.9504. Min Range: -0.9504

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1998574 (The Pile)

Max Activating Token Index: 630