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

Dataset: The Pile

Neuron 1679 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.3655. Min Act: -0.0000

Data Index: 894271 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.2461. Min Act: -0.0000

Data Index: 456002 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1569. Min Act: -0.0000

Data Index: 57213 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1315805 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1322. Min Act: -0.0000

Data Index: 255022 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1375826 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0464. Min Act: -0.0000

Data Index: 925860 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9133. Min Act: -0.0000

Data Index: 504782 (The Pile)

Max Activating Token Index: 874

Text #8

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1022. Min Act: -0.0000

Data Index: 405236 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1025. Min Act: -0.0000

Data Index: 274526 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1060. Min Act: -0.0000

Data Index: 1553418 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0267. Min Act: -0.0000

Data Index: 573261 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0173. Min Act: -0.0000

Data Index: 320697 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9984. Min Act: -0.0000

Data Index: 963921 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1890506 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0278. Min Act: -0.0000

Data Index: 746819 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9570. Min Act: -0.0000

Data Index: 769631 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9389. Min Act: -0.0000

Data Index: 472820 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9266. Min Act: -0.0000

Data Index: 995737 (The Pile)

Max Activating Token Index: 1002

Text #19

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9818. Min Act: -0.0000

Data Index: 39850 (The Pile)

Max Activating Token Index: 564