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

Dataset: The Pile

Neuron 287 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: 1.1143. Min Range: -1.1143

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1002444 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 1.1143. Min Range: -1.1143

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1315521 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.9886. Min Act: -0.0000

Data Index: 74830 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.9441. Min Act: -0.0000

Data Index: 1494060 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1749377 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.9018. Min Act: -0.0000

Data Index: 149734 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7947. Min Act: -0.0000

Data Index: 537664 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1345931 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1420685 (The Pile)

Max Activating Token Index: 452

Text #9

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1582355 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6156. Min Act: -0.0000

Data Index: 48903 (The Pile)

Max Activating Token Index: 911

Text #11

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7179. Min Act: 0.0000

Data Index: 526916 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.7133. Min Act: -0.0000

Data Index: 413068 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6695. Min Act: -0.0000

Data Index: 628464 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6278. Min Act: -0.0000

Data Index: 319943 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1063099 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1985490 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6192. Min Act: -0.0000

Data Index: 22094 (The Pile)

Max Activating Token Index: 372

Text #18

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1610476 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 1.1143. Min Range: -1.1143

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1247433 (The Pile)

Max Activating Token Index: 414