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

Dataset: The Pile

Neuron 1077 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: 0.8620. Min Range: -0.8620

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1895287 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1040252 (The Pile)

Max Activating Token Index: 624

Text #2

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7601. Min Act: -0.0000

Data Index: 939537 (The Pile)

Max Activating Token Index: 628

Text #3

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6984. Min Act: -0.0001

Data Index: 841823 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6562. Min Act: -0.0000

Data Index: 664372 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1041280 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1670318 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1904490 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6417. Min Act: -0.0000

Data Index: 21204 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6137. Min Act: -0.0000

Data Index: 772200 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1893558 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1103785 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1769595 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6238. Min Act: -0.0000

Data Index: 738741 (The Pile)

Max Activating Token Index: 337

Text #14

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6117. Min Act: -0.0000

Data Index: 265638 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1607094 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1803420 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1111802 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1487075 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 0.8620. Min Range: -0.8620

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1738796 (The Pile)

Max Activating Token Index: 531