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

Dataset: The Pile

Neuron 203 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: 1.6490. Min Range: -1.6490

Max Act: 1.6490. Min Act: -0.0000

Data Index: 1285836 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.6055. Min Act: -0.0000

Data Index: 379410 (The Pile)

Max Activating Token Index: 720

Text #2

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4789. Min Act: -0.0000

Data Index: 718380 (The Pile)

Max Activating Token Index: 760

Text #3

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5627. Min Act: -0.0000

Data Index: 1953731 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4652. Min Act: -0.0000

Data Index: 597244 (The Pile)

Max Activating Token Index: 716

Text #5

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5433. Min Act: -0.0000

Data Index: 485663 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5058. Min Act: -0.0000

Data Index: 195266 (The Pile)

Max Activating Token Index: 717

Text #7

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4135. Min Act: -0.0000

Data Index: 318140 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.3996. Min Act: -0.0000

Data Index: 1315840 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1585895 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.5538. Min Act: -0.0000

Data Index: 1994685 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.3736. Min Act: -0.0000

Data Index: 833479 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.3667. Min Act: -0.0000

Data Index: 968681 (The Pile)

Max Activating Token Index: 839

Text #13

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1688329 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4251. Min Act: -0.0000

Data Index: 1646436 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4067. Min Act: -0.0000

Data Index: 1329042 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1130618 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1961316 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4074. Min Act: -0.0000

Data Index: 238538 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4073. Min Act: -0.0000

Data Index: 1938816 (The Pile)

Max Activating Token Index: 977