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

Dataset: The Pile

Neuron 268 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.6024. Min Act: -0.0000

Data Index: 1805086 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.6804. Min Act: -0.0000

Data Index: 1397637 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.5179. Min Act: -0.0000

Data Index: 1539894 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.6951. Min Act: -0.0000

Data Index: 566448 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.4956. Min Act: -0.0000

Data Index: 1994272 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.2792. Min Act: -0.0000

Data Index: 780502 (The Pile)

Max Activating Token Index: 821

Text #6

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.3583. Min Act: -0.0000

Data Index: 399301 (The Pile)

Max Activating Token Index: 593

Text #7

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.3397. Min Act: -0.0000

Data Index: 735811 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 3.6951. Min Range: -3.6951

Max Act: 2.7650. Min Act: -0.0000

Data Index: 1973686 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 3.6951. Min Range: -3.6951

Max Act: 2.7408. Min Act: -0.0000

Data Index: 598746 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.0988. Min Act: -0.0000

Data Index: 1824255 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.3844. Min Act: -0.0000

Data Index: 1833807 (The Pile)

Max Activating Token Index: 959

Text #12

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.3695. Min Act: -0.0000

Data Index: 503633 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.0302. Min Act: -0.0000

Data Index: 950399 (The Pile)

Max Activating Token Index: 517

Text #14

Max Range: 3.6951. Min Range: -3.6951

Max Act: 2.9009. Min Act: -0.0000

Data Index: 1919883 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.1039. Min Act: -0.0000

Data Index: 1548213 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 3.6951. Min Range: -3.6951

Max Act: 2.5715. Min Act: -0.0000

Data Index: 947029 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 3.6951. Min Range: -3.6951

Max Act: 2.6555. Min Act: -0.0000

Data Index: 855653 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 3.6951. Min Range: -3.6951

Max Act: 2.8894. Min Act: -0.0000

Data Index: 1729873 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 3.6951. Min Range: -3.6951

Max Act: 3.0292. Min Act: -0.0000

Data Index: 1698783 (The Pile)

Max Activating Token Index: 654