Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2985 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1854525 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4571. Min Act: -0.0000

Data Index: 59615 (The Pile)

Max Activating Token Index: 564

Text #2

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1362040 (The Pile)

Max Activating Token Index: 283

Text #3

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1454675 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4225. Min Act: -0.0000

Data Index: 173237 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1048513 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4546. Min Act: -0.0000

Data Index: 408201 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4400. Min Act: -0.0000

Data Index: 918558 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4218. Min Act: -0.0000

Data Index: 457707 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4507. Min Act: -0.0000

Data Index: 663744 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4248. Min Act: -0.0000

Data Index: 953587 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1641904 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1726047 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1250769 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1612684 (The Pile)

Max Activating Token Index: 530

Text #15

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1503609 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1194348 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3915. Min Act: -0.0000

Data Index: 840838 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1363908 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 0.4937. Min Range: -0.4937

Max Act: 0.4168. Min Act: -0.0000

Data Index: 159811 (The Pile)

Max Activating Token Index: 205