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

Dataset: The Pile

Neuron 3572 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.5660. Min Act: -0.0000

Data Index: 550840 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.4402. Min Act: -0.0000

Data Index: 66408 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2006. Min Act: -0.0000

Data Index: 1919534 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1366336 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2151. Min Act: -0.0000

Data Index: 1584260 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1136643 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.1035. Min Act: -0.0000

Data Index: 371670 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1210191 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0187. Min Act: -0.0000

Data Index: 309084 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0240. Min Act: -0.0000

Data Index: 1575952 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0809. Min Act: -0.0000

Data Index: 330404 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1951037 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1818767 (The Pile)

Max Activating Token Index: 418

Text #13

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.1247. Min Act: -0.0000

Data Index: 1371370 (The Pile)

Max Activating Token Index: 936

Text #14

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.9208. Min Act: -0.0000

Data Index: 719745 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1150297 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.9313. Min Act: -0.0000

Data Index: 151410 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0152. Min Act: -0.0000

Data Index: 197618 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1061442 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1991754 (The Pile)

Max Activating Token Index: 398