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

Dataset: The Pile

Neuron 1981 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2311. Min Act: -0.0000

Data Index: 181887 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2071. Min Act: -0.0000

Data Index: 281678 (The Pile)

Max Activating Token Index: 434

Text #2

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2339. Min Act: -0.0000

Data Index: 572226 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2244. Min Act: -0.0000

Data Index: 924162 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1826608 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1637. Min Act: -0.0000

Data Index: 502745 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1849033 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1832946 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1459965 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2078. Min Act: -0.0000

Data Index: 941126 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1872. Min Act: -0.0000

Data Index: 761065 (The Pile)

Max Activating Token Index: 339

Text #11

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2060. Min Act: -0.0000

Data Index: 923960 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1674668 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1640. Min Act: -0.0000

Data Index: 960981 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1927. Min Act: -0.0000

Data Index: 73276 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1566. Min Act: -0.0000

Data Index: 829613 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1575. Min Act: -0.0000

Data Index: 832698 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1154367 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1365. Min Act: -0.0000

Data Index: 572505 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1688. Min Act: -0.0000

Data Index: 117370 (The Pile)

Max Activating Token Index: 87