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

Dataset: The Pile

Neuron 2093 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: 1.2993. Min Range: -1.2993

Max Act: 1.2993. Min Act: -0.0000

Data Index: 1517043 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.2703. Min Act: -0.0000

Data Index: 361401 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1384633 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0676. Min Act: -0.0000

Data Index: 1838192 (The Pile)

Max Activating Token Index: 804

Text #4

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1951939 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.1067. Min Act: -0.0000

Data Index: 991639 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.1012. Min Act: -0.0000

Data Index: 391029 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0440. Min Act: -0.0000

Data Index: 342066 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1623781 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0102. Min Act: -0.0000

Data Index: 634342 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0301. Min Act: -0.0000

Data Index: 486339 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1559925 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1901005 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0272. Min Act: -0.0000

Data Index: 150092 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9877. Min Act: -0.0000

Data Index: 829123 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0140. Min Act: -0.0000

Data Index: 13123 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9391. Min Act: -0.0000

Data Index: 855554 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1465797 (The Pile)

Max Activating Token Index: 830

Text #18

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1079995 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1943570 (The Pile)

Max Activating Token Index: 467