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

Dataset: The Pile

Neuron 3996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1157709 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1405834 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1339855 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4907. Min Act: -0.0000

Data Index: 25714 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1337025 (The Pile)

Max Activating Token Index: 6

Text #5

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1581652 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4566. Min Act: -0.0000

Data Index: 884800 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4593. Min Act: -0.0000

Data Index: 919331 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1843092 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4155. Min Act: -0.0000

Data Index: 135755 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1162848 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4177. Min Act: -0.0000

Data Index: 677230 (The Pile)

Max Activating Token Index: 801

Text #12

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4159. Min Act: -0.0000

Data Index: 881430 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1263205 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4200. Min Act: -0.0000

Data Index: 88203 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1730549 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.3968. Min Act: -0.0000

Data Index: 679640 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1465173 (The Pile)

Max Activating Token Index: 936

Text #18

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1382984 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.5586. Min Range: -0.5586

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1105304 (The Pile)

Max Activating Token Index: 785