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

Dataset: The Pile

Neuron 1361 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.5394. Min Act: -0.0000

Data Index: 495222 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.2912. Min Act: -0.0000

Data Index: 313316 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.2986. Min Act: -0.0000

Data Index: 1432325 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.3187. Min Act: -0.0000

Data Index: 1648503 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.2633. Min Act: -0.0000

Data Index: 929838 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.0690. Min Act: -0.0000

Data Index: 598815 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.4043. Min Act: -0.0000

Data Index: 8279 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.2139. Min Act: -0.0000

Data Index: 52303 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.1750. Min Act: -0.0000

Data Index: 892350 (The Pile)

Max Activating Token Index: 786

Text #9

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.4720. Min Act: -0.0000

Data Index: 1471736 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.0845. Min Act: -0.0000

Data Index: 1570559 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.0445. Min Act: -0.0000

Data Index: 258850 (The Pile)

Max Activating Token Index: 532

Text #12

Max Range: 3.5394. Min Range: -3.5394

Max Act: 3.0313. Min Act: -0.0000

Data Index: 1077231 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 3.5394. Min Range: -3.5394

Max Act: 2.7562. Min Act: -0.0000

Data Index: 1445035 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 3.5394. Min Range: -3.5394

Max Act: 2.8772. Min Act: -0.0000

Data Index: 918024 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 3.5394. Min Range: -3.5394

Max Act: 2.9074. Min Act: -0.0000

Data Index: 1581045 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 3.5394. Min Range: -3.5394

Max Act: 2.9161. Min Act: -0.0000

Data Index: 1621099 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 3.5394. Min Range: -3.5394

Max Act: 2.6908. Min Act: -0.0000

Data Index: 1053150 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 3.5394. Min Range: -3.5394

Max Act: 2.6442. Min Act: -0.0000

Data Index: 714283 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 3.5394. Min Range: -3.5394

Max Act: 2.4232. Min Act: -0.0000

Data Index: 959501 (The Pile)

Max Activating Token Index: 797