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

Dataset: The Pile

Neuron 1551 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.6243. Min Act: -0.0000

Data Index: 1772207 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.7043. Min Act: -0.0000

Data Index: 1451391 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.7609. Min Act: -0.0000

Data Index: 609072 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.6003. Min Act: -0.0000

Data Index: 1489227 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.9054. Min Act: -0.0000

Data Index: 470996 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.6044. Min Act: -0.0000

Data Index: 1505448 (The Pile)

Max Activating Token Index: 924

Text #6

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.2014. Min Act: -0.0000

Data Index: 253084 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8002. Min Act: -0.0000

Data Index: 1428863 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.2158. Min Act: -0.0000

Data Index: 707425 (The Pile)

Max Activating Token Index: 259

Text #9

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.3930. Min Act: -0.0000

Data Index: 83316 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.3574. Min Act: -0.0000

Data Index: 1552095 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.3211. Min Act: -0.0000

Data Index: 717473 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.3223. Min Act: -0.0000

Data Index: 1481863 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.2756. Min Act: -0.0000

Data Index: 1517047 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.4325. Min Act: -0.0000

Data Index: 765624 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.8731. Min Act: -0.0000

Data Index: 1264844 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.2335. Min Act: -0.0000

Data Index: 76606 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.4630. Min Act: -0.0000

Data Index: 697199 (The Pile)

Max Activating Token Index: 838

Text #18

Max Range: 3.9054. Min Range: -3.9054

Max Act: 3.1683. Min Act: -0.0000

Data Index: 1121465 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 3.9054. Min Range: -3.9054

Max Act: 2.9915. Min Act: -0.0000

Data Index: 1119327 (The Pile)

Max Activating Token Index: 584