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

Dataset: The Pile

Neuron 417 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: 3.7497. Min Range: -3.7497

Max Act: 3.7497. Min Act: -0.0000

Data Index: 477789 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 3.7497. Min Range: -3.7497

Max Act: 2.4816. Min Act: -0.0000

Data Index: 1685241 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 3.7497. Min Range: -3.7497

Max Act: 2.3653. Min Act: -0.0000

Data Index: 560086 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 3.7497. Min Range: -3.7497

Max Act: 2.6054. Min Act: -0.0000

Data Index: 1848021 (The Pile)

Max Activating Token Index: 902

Text #4

Max Range: 3.7497. Min Range: -3.7497

Max Act: 2.3141. Min Act: -0.0000

Data Index: 665413 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.8180. Min Act: -0.0000

Data Index: 539666 (The Pile)

Max Activating Token Index: 234

Text #6

Max Range: 3.7497. Min Range: -3.7497

Max Act: 2.3330. Min Act: -0.0000

Data Index: 1103723 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 3.7497. Min Range: -3.7497

Max Act: 2.2156. Min Act: -0.0000

Data Index: 265301 (The Pile)

Max Activating Token Index: 510

Text #8

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.8639. Min Act: -0.0000

Data Index: 1537081 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 3.7497. Min Range: -3.7497

Max Act: 2.5103. Min Act: -0.0000

Data Index: 1575475 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.8636. Min Act: -0.0000

Data Index: 1614671 (The Pile)

Max Activating Token Index: 988

Text #11

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.8936. Min Act: -0.0000

Data Index: 242053 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.7728. Min Act: -0.0000

Data Index: 1723841 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.3238. Min Act: -0.0000

Data Index: 57621 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.7756. Min Act: -0.0000

Data Index: 315988 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.6784. Min Act: -0.0000

Data Index: 718617 (The Pile)

Max Activating Token Index: 849

Text #16

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.6410. Min Act: -0.0000

Data Index: 871465 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.6353. Min Act: -0.0000

Data Index: 988592 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.6116. Min Act: -0.0000

Data Index: 575313 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 3.7497. Min Range: -3.7497

Max Act: 1.4782. Min Act: -0.0000

Data Index: 641492 (The Pile)

Max Activating Token Index: 946