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

Dataset: The Pile

Neuron 4076 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.5103. Min Act: -0.0000

Data Index: 1913367 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.4473. Min Act: -0.0000

Data Index: 854418 (The Pile)

Max Activating Token Index: 160

Text #2

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.3588. Min Act: -0.0000

Data Index: 884542 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.0177. Min Act: -0.0000

Data Index: 991657 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 1.5103. Min Range: -1.5103

Max Act: 1.0454. Min Act: -0.0000

Data Index: 193571 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.9347. Min Act: -0.0000

Data Index: 632342 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1213201 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.8801. Min Act: -0.0000

Data Index: 212690 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1903803 (The Pile)

Max Activating Token Index: 560

Text #9

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1124891 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1106852 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7043. Min Act: -0.0000

Data Index: 847194 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1322253 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1936834 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1042183 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7877. Min Act: -0.0000

Data Index: 89768 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1424198 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1418648 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7592. Min Act: -0.0000

Data Index: 753565 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 1.5103. Min Range: -1.5103

Max Act: 0.7983. Min Act: -0.0000

Data Index: 962431 (The Pile)

Max Activating Token Index: 787