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

Dataset: The Pile

Neuron 1013 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: 0.3133. Min Range: -0.3133

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1008269 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2895. Min Act: -0.0000

Data Index: 475693 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2526. Min Act: -0.0000

Data Index: 127370 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1114955 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1867885 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1656158 (The Pile)

Max Activating Token Index: 1008

Text #6

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2734. Min Act: -0.0000

Data Index: 463938 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1383500 (The Pile)

Max Activating Token Index: 862

Text #8

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2158. Min Act: -0.0000

Data Index: 295743 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1621024 (The Pile)

Max Activating Token Index: 618

Text #10

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2653. Min Act: -0.0000

Data Index: 128751 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1884702 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1850169 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2518. Min Act: -0.0000

Data Index: 829549 (The Pile)

Max Activating Token Index: 541

Text #14

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1752581 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1321544 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1695703 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2746. Min Act: -0.0000

Data Index: 509497 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2270. Min Act: -0.0000

Data Index: 803356 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2405. Min Act: -0.0000

Data Index: 1312277 (The Pile)

Max Activating Token Index: 911