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

Dataset: The Pile

Neuron 3270 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: 1.7427. Min Range: -1.7427

Max Act: 1.6554. Min Act: -0.0000

Data Index: 636997 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.7080. Min Act: -0.0000

Data Index: 1477920 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.7001. Min Act: -0.0000

Data Index: 384645 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.6835. Min Act: -0.0000

Data Index: 371931 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.7427. Min Act: -0.0000

Data Index: 1927875 (The Pile)

Max Activating Token Index: 403

Text #5

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.6124. Min Act: -0.0000

Data Index: 798337 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5182. Min Act: -0.0000

Data Index: 300980 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5045. Min Act: -0.0000

Data Index: 511296 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5808. Min Act: -0.0000

Data Index: 1907544 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.7040. Min Act: -0.0000

Data Index: 1370737 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1798562 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.4785. Min Act: -0.0000

Data Index: 360960 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5650. Min Act: -0.0000

Data Index: 1545170 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5598. Min Act: -0.0000

Data Index: 482678 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5095. Min Act: -0.0000

Data Index: 1710500 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.6099. Min Act: -0.0000

Data Index: 1457802 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5095. Min Act: -0.0000

Data Index: 1212193 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.6382. Min Act: -0.0000

Data Index: 760131 (The Pile)

Max Activating Token Index: 277

Text #18

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5451. Min Act: -0.0000

Data Index: 652813 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 1.7427. Min Range: -1.7427

Max Act: 1.5285. Min Act: -0.0000

Data Index: 1262510 (The Pile)

Max Activating Token Index: 285