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

Dataset: The Pile

Neuron 1985 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1304. Min Range: -3.1304

Max Act: 3.1304. Min Act: -0.0000

Data Index: 1682928 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.6644. Min Act: -0.0000

Data Index: 66030 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.9009. Min Act: -0.0000

Data Index: 1349136 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.5991. Min Act: -0.0000

Data Index: 460589 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.6787. Min Act: -0.0000

Data Index: 1156367 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.4567. Min Act: -0.0000

Data Index: 496288 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.2402. Min Act: -0.0000

Data Index: 82080 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.3413. Min Act: -0.0000

Data Index: 1027906 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.4137. Min Act: -0.0000

Data Index: 1945730 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.1296. Min Act: -0.0000

Data Index: 842571 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.0490. Min Act: -0.0000

Data Index: 1411686 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.2418. Min Act: -0.0000

Data Index: 1980659 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.3365. Min Act: -0.0000

Data Index: 1087896 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.5366. Min Act: -0.0000

Data Index: 209413 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.0434. Min Act: -0.0000

Data Index: 1996347 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.1304. Min Act: -0.0000

Data Index: 1369944 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.0396. Min Act: -0.0000

Data Index: 1589901 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.0855. Min Act: -0.0000

Data Index: 638064 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 3.1304. Min Range: -3.1304

Max Act: 2.1747. Min Act: -0.0000

Data Index: 1292390 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 3.1304. Min Range: -3.1304

Max Act: 1.9789. Min Act: -0.0000

Data Index: 1910052 (The Pile)

Max Activating Token Index: 771