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

Dataset: The Pile

Neuron 2289 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: 0.4498. Min Range: -0.4498

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1230803 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.4217. Min Act: -0.0000

Data Index: 491359 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1960759 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.4115. Min Act: 0.0001

Data Index: 151812 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1165763 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3861. Min Act: -0.0000

Data Index: 408496 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1463137 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3605. Min Act: -0.0000

Data Index: 769959 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3681. Min Act: -0.0000

Data Index: 830461 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1255635 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3550. Min Act: -0.0000

Data Index: 437138 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3381. Min Act: 0.0000

Data Index: 1943893 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1501169 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3427. Min Act: -0.0000

Data Index: 596509 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1105421 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1909181 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1633641 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3266. Min Act: -0.0000

Data Index: 883112 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1521157 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3338. Min Act: -0.0000

Data Index: 726415 (The Pile)

Max Activating Token Index: 295