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

Dataset: The Pile

Neuron 4239 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: 3.4284. Min Range: -3.4284

Max Act: 3.3423. Min Act: -0.0000

Data Index: 19650 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.4284. Min Act: -0.0000

Data Index: 682807 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.3334. Min Act: -0.0000

Data Index: 410754 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.2484. Min Act: -0.0000

Data Index: 1490746 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.2451. Min Act: -0.0000

Data Index: 1241664 (The Pile)

Max Activating Token Index: 1018

Text #5

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.1649. Min Act: -0.0000

Data Index: 1968998 (The Pile)

Max Activating Token Index: 156

Text #6

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.1772. Min Act: -0.0000

Data Index: 1466443 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.1462. Min Act: -0.0000

Data Index: 1963644 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.1293. Min Act: -0.0000

Data Index: 781182 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.2710. Min Act: -0.0000

Data Index: 1991492 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.1259. Min Act: -0.0000

Data Index: 663148 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.9698. Min Act: -0.0000

Data Index: 997663 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.9582. Min Act: -0.0000

Data Index: 1027003 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.2367. Min Act: -0.0000

Data Index: 1267038 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.0811. Min Act: -0.0000

Data Index: 908845 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.9219. Min Act: -0.0000

Data Index: 62434 (The Pile)

Max Activating Token Index: 488

Text #16

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.0755. Min Act: -0.0000

Data Index: 1018973 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.1968. Min Act: -0.0000

Data Index: 1849892 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.9138. Min Act: -0.0000

Data Index: 1239040 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.2026. Min Act: -0.0000

Data Index: 1318541 (The Pile)

Max Activating Token Index: 862