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

Dataset: The Pile

Neuron 4768 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: 5.5804. Min Range: -5.5804

Max Act: 5.4183. Min Act: -0.0000

Data Index: 1709206 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.3320. Min Act: -0.0000

Data Index: 1647888 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.3238. Min Act: -0.0000

Data Index: 1087838 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.4791. Min Act: -0.0000

Data Index: 389968 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.4523. Min Act: -0.0000

Data Index: 1692783 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.2701. Min Act: -0.0000

Data Index: 689810 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.4379. Min Act: -0.0000

Data Index: 549127 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.5804. Min Act: -0.0000

Data Index: 1791534 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.1533. Min Act: -0.0000

Data Index: 1738113 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 5.5804. Min Range: -5.5804

Max Act: 4.9842. Min Act: -0.0000

Data Index: 1188614 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.3029. Min Act: -0.0000

Data Index: 1471653 (The Pile)

Max Activating Token Index: 229

Text #11

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.2754. Min Act: -0.0000

Data Index: 774260 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.0989. Min Act: -0.0000

Data Index: 1100579 (The Pile)

Max Activating Token Index: 192

Text #13

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.0852. Min Act: -0.0000

Data Index: 1900354 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.0811. Min Act: -0.0000

Data Index: 1500754 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.4488. Min Act: -0.0000

Data Index: 409859 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 5.5804. Min Range: -5.5804

Max Act: 4.9754. Min Act: -0.0000

Data Index: 197910 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.3483. Min Act: -0.0000

Data Index: 1661797 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.1049. Min Act: -0.0000

Data Index: 642332 (The Pile)

Max Activating Token Index: 237

Text #19

Max Range: 5.5804. Min Range: -5.5804

Max Act: 5.0952. Min Act: -0.0000

Data Index: 1294325 (The Pile)

Max Activating Token Index: 173