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

Dataset: The Pile

Neuron 2291 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1104364 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7736. Min Act: -0.0000

Data Index: 846313 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1881289 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1528404 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6949. Min Act: -0.0000

Data Index: 69085 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1330819 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5796. Min Act: -0.0000

Data Index: 247359 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6816. Min Act: -0.0000

Data Index: 697096 (The Pile)

Max Activating Token Index: 777

Text #8

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5961. Min Act: -0.0000

Data Index: 468630 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1835029 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1995076 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5459. Min Act: -0.0000

Data Index: 143169 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1925158 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6468. Min Act: -0.0000

Data Index: 153514 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5508. Min Act: -0.0000

Data Index: 168345 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1742486 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.6017. Min Act: 0.0000

Data Index: 1408049 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1190083 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5416. Min Act: -0.0000

Data Index: 861270 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 0.8258. Min Range: -0.8258

Max Act: 0.5510. Min Act: 0.0000

Data Index: 475738 (The Pile)

Max Activating Token Index: 575