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

Dataset: The Pile

Neuron 1529 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: 0.4659. Min Range: -0.4659

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1585210 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1368300 (The Pile)

Max Activating Token Index: 603

Text #2

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1253220 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1680233 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3663. Min Act: -0.0000

Data Index: 45784 (The Pile)

Max Activating Token Index: 214

Text #5

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1182322 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3249. Min Act: -0.0000

Data Index: 624323 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3574. Min Act: 0.0000

Data Index: 1394762 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1988011 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3361. Min Act: -0.0000

Data Index: 188035 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3517. Min Act: -0.0000

Data Index: 368107 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3333. Min Act: 0.0000

Data Index: 1337202 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3321. Min Act: -0.0000

Data Index: 268901 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3378. Min Act: -0.0000

Data Index: 515915 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1247621 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1700716 (The Pile)

Max Activating Token Index: 814

Text #16

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3156. Min Act: -0.0000

Data Index: 740684 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3110. Min Act: 0.0000

Data Index: 1073559 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3022. Min Act: -0.0000

Data Index: 571191 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3254. Min Act: 0.0000

Data Index: 366047 (The Pile)

Max Activating Token Index: 75