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

Dataset: The Pile

Neuron 2242 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0358. Min Range: -1.0358

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1645668 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1226078 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1982460 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8585. Min Act: -0.0000

Data Index: 990074 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1966953 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8330. Min Act: -0.0000

Data Index: 860558 (The Pile)

Max Activating Token Index: 364

Text #6

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1535355 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1312202 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1730515 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1222792 (The Pile)

Max Activating Token Index: 1007

Text #10

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7827. Min Act: -0.0000

Data Index: 97580 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7243. Min Act: -0.0000

Data Index: 306507 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1706469 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6670. Min Act: -0.0000

Data Index: 858189 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6435. Min Act: -0.0000

Data Index: 698797 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1722305 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6496. Min Act: -0.0000

Data Index: 626699 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.6624. Min Act: -0.0000

Data Index: 252954 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7478. Min Act: 0.0000

Data Index: 669875 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 1.0358. Min Range: -1.0358

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1611821 (The Pile)

Max Activating Token Index: 334