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

Dataset: The Pile

Neuron 1532 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: 1.7517. Min Range: -1.7517

Max Act: 1.7517. Min Act: -0.0000

Data Index: 524701 (The Pile)

Max Activating Token Index: 895

Text #1

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.3795. Min Act: -0.0000

Data Index: 738098 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1378500 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4076. Min Act: -0.0000

Data Index: 647721 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4390. Min Act: -0.0000

Data Index: 717949 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.3870. Min Act: -0.0000

Data Index: 495308 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4059. Min Act: -0.0000

Data Index: 1734593 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.4114. Min Act: -0.0000

Data Index: 1471670 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.2006. Min Act: -0.0000

Data Index: 147804 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1038178 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.2568. Min Act: -0.0000

Data Index: 838515 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1133629 (The Pile)

Max Activating Token Index: 965

Text #12

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.0926. Min Act: -0.0000

Data Index: 316091 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1060170 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.2126. Min Act: -0.0000

Data Index: 192612 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1282498 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.2157. Min Act: -0.0000

Data Index: 185495 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1987590 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1722945 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 1.7517. Min Range: -1.7517

Max Act: 1.1056. Min Act: -0.0000

Data Index: 936517 (The Pile)

Max Activating Token Index: 566