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

Dataset: The Pile

Neuron 1051 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.1620. Min Act: -0.0000

Data Index: 1811885 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1014966 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 1.1620. Min Range: -1.1620

Max Act: 1.0300. Min Act: -0.0000

Data Index: 601109 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1476309 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1493665 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1677926 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9547. Min Act: -0.0000

Data Index: 625374 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9781. Min Act: -0.0000

Data Index: 759437 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1129639 (The Pile)

Max Activating Token Index: 284

Text #9

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1465498 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9035. Min Act: -0.0000

Data Index: 895194 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9377. Min Act: -0.0000

Data Index: 790496 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9219. Min Act: -0.0000

Data Index: 547194 (The Pile)

Max Activating Token Index: 403

Text #13

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9241. Min Act: -0.0000

Data Index: 196985 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9133. Min Act: -0.0000

Data Index: 330674 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1763545 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1447501 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1256045 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9001. Min Act: -0.0000

Data Index: 579116 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 1.1620. Min Range: -1.1620

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1441691 (The Pile)

Max Activating Token Index: 90