Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3807 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.2237. Min Act: -0.0000

Data Index: 179892 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1567039 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1411855 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1040316 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1409460 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8788. Min Act: -0.0000

Data Index: 280336 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1761282 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1235134 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1635635 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8201. Min Act: -0.0000

Data Index: 382022 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8188. Min Act: -0.0000

Data Index: 865924 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.7923. Min Act: 0.0000

Data Index: 581319 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1049250 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1213449 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.7420. Min Act: -0.0000

Data Index: 978984 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1695062 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8020. Min Act: -0.0000

Data Index: 981008 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1317869 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.8294. Min Act: -0.0000

Data Index: 560058 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 1.2237. Min Range: -1.2237

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1686872 (The Pile)

Max Activating Token Index: 567