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

Dataset: The Pile

Neuron 701 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.5435. Min Range: -9.5435

Max Act: 9.5435. Min Act: -0.0000

Data Index: 1689702 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 9.5435. Min Range: -9.5435

Max Act: 9.3638. Min Act: -0.0000

Data Index: 1965717 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 9.5435. Min Range: -9.5435

Max Act: 9.5171. Min Act: -0.0000

Data Index: 688099 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 9.5435. Min Range: -9.5435

Max Act: 8.3667. Min Act: -0.0000

Data Index: 1138480 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.9345. Min Act: -0.0000

Data Index: 560933 (The Pile)

Max Activating Token Index: 269

Text #5

Max Range: 9.5435. Min Range: -9.5435

Max Act: 8.0177. Min Act: -0.0000

Data Index: 1232257 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 9.5435. Min Range: -9.5435

Max Act: 8.0574. Min Act: -0.0000

Data Index: 1602895 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 9.5435. Min Range: -9.5435

Max Act: 8.0646. Min Act: -0.0000

Data Index: 1272249 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.2600. Min Act: -0.0000

Data Index: 839399 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.6504. Min Act: -0.0000

Data Index: 859798 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.4022. Min Act: -0.0000

Data Index: 1831315 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.1873. Min Act: -0.0000

Data Index: 1465328 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.9258. Min Act: -0.0000

Data Index: 60492 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.2246. Min Act: -0.0000

Data Index: 46600 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.0748. Min Act: -0.0000

Data Index: 846723 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.4649. Min Act: -0.0000

Data Index: 764618 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.2279. Min Act: -0.0000

Data Index: 109302 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.3598. Min Act: -0.0000

Data Index: 1552145 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.4167. Min Act: -0.0000

Data Index: 1971239 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 9.5435. Min Range: -9.5435

Max Act: 7.8862. Min Act: -0.0000

Data Index: 1218804 (The Pile)

Max Activating Token Index: 475