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

Dataset: The Pile

Neuron 3168 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: 0.8141. Min Range: -0.8141

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1817483 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1163861 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1065652 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1540249 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6584. Min Act: -0.0000

Data Index: 724552 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7379. Min Act: -0.0000

Data Index: 894209 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7164. Min Act: -0.0000

Data Index: 871536 (The Pile)

Max Activating Token Index: 843

Text #7

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1544835 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1426371 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1401822 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6383. Min Act: -0.0000

Data Index: 238226 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1770972 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6346. Min Act: -0.0000

Data Index: 913966 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1567847 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6482. Min Act: -0.0000

Data Index: 952694 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1676953 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6287. Min Act: -0.0000

Data Index: 271499 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1187502 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1098670 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6228. Min Act: -0.0000

Data Index: 918745 (The Pile)

Max Activating Token Index: 89