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

Dataset: The Pile

Neuron 2307 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: 0.2586. Min Range: -0.2586

Max Act: 0.2586. Min Act: -0.0000

Data Index: 259688 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1579026 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1459271 (The Pile)

Max Activating Token Index: 508

Text #3

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2177. Min Act: -0.0000

Data Index: 99125 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1994956 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1995. Min Act: -0.0000

Data Index: 137600 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1835. Min Act: -0.0000

Data Index: 473708 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1746. Min Act: -0.0000

Data Index: 759977 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1956. Min Act: -0.0000

Data Index: 81013 (The Pile)

Max Activating Token Index: 730

Text #9

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1901364 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1439539 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1753. Min Act: -0.0000

Data Index: 916283 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.2044. Min Act: -0.0000

Data Index: 909750 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1670. Min Act: -0.0000

Data Index: 992772 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1744470 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1813. Min Act: -0.0000

Data Index: 910541 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1488627 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1686. Min Act: -0.0000

Data Index: 755982 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1532. Min Act: -0.0000

Data Index: 409016 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.2586. Min Range: -0.2586

Max Act: 0.1629. Min Act: -0.0000

Data Index: 823055 (The Pile)

Max Activating Token Index: 903