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

Dataset: The Pile

Neuron 5067 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.9321. Min Act: 0.0000

Data Index: 1180128 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8968. Min Act: 0.0000

Data Index: 860427 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1404007 (The Pile)

Max Activating Token Index: 411

Text #3

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1051175 (The Pile)

Max Activating Token Index: 683

Text #4

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8769. Min Act: 0.0000

Data Index: 200609 (The Pile)

Max Activating Token Index: 721

Text #5

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1562467 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8807. Min Act: 0.0001

Data Index: 1719922 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8363. Min Act: -0.0000

Data Index: 60632 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1642336 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1250693 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1401698 (The Pile)

Max Activating Token Index: 971

Text #11

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8202. Min Act: -0.0000

Data Index: 466526 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1132272 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1010503 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7436. Min Act: -0.0000

Data Index: 322451 (The Pile)

Max Activating Token Index: 502

Text #15

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7140. Min Act: 0.0000

Data Index: 1415882 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6768. Min Act: 0.0000

Data Index: 1079490 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1434996 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7135. Min Act: -0.0000

Data Index: 11143 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7001. Min Act: 0.0000

Data Index: 1535924 (The Pile)

Max Activating Token Index: 774