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

Dataset: The Pile

Neuron 1578 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: 5.7230. Min Range: -5.7230

Max Act: 5.7230. Min Act: -0.0000

Data Index: 383287 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.4336. Min Act: -0.0000

Data Index: 114498 (The Pile)

Max Activating Token Index: 765

Text #2

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.0396. Min Act: -0.0000

Data Index: 130081 (The Pile)

Max Activating Token Index: 999

Text #3

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.1114. Min Act: -0.0000

Data Index: 1347507 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.2818. Min Act: -0.0000

Data Index: 1162422 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.0719. Min Act: -0.0000

Data Index: 1457518 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.0371. Min Act: -0.0000

Data Index: 1325601 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.2234. Min Act: -0.0000

Data Index: 1280465 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.0264. Min Act: -0.0000

Data Index: 1736713 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.3793. Min Act: -0.0000

Data Index: 1257940 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.1608. Min Act: -0.0000

Data Index: 888368 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 5.7230. Min Range: -5.7230

Max Act: 4.2017. Min Act: -0.0000

Data Index: 1984839 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 5.7230. Min Range: -5.7230

Max Act: 4.8016. Min Act: -0.0000

Data Index: 1926511 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.1107. Min Act: -0.0000

Data Index: 238314 (The Pile)

Max Activating Token Index: 46

Text #14

Max Range: 5.7230. Min Range: -5.7230

Max Act: 4.9557. Min Act: -0.0000

Data Index: 1253884 (The Pile)

Max Activating Token Index: 170

Text #15

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.1018. Min Act: -0.0000

Data Index: 1558337 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.0615. Min Act: -0.0000

Data Index: 367970 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 5.7230. Min Range: -5.7230

Max Act: 4.8811. Min Act: -0.0000

Data Index: 601305 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 5.7230. Min Range: -5.7230

Max Act: 5.0591. Min Act: -0.0000

Data Index: 1729267 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 5.7230. Min Range: -5.7230

Max Act: 4.8022. Min Act: -0.0000

Data Index: 793874 (The Pile)

Max Activating Token Index: 107