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

Dataset: The Pile

Neuron 874 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.6585. Min Range: -10.6585

Max Act: 10.6585. Min Act: -0.0000

Data Index: 196092 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 10.6585. Min Range: -10.6585

Max Act: 10.6426. Min Act: -0.0000

Data Index: 1378742 (The Pile)

Max Activating Token Index: 348

Text #2

Max Range: 10.6585. Min Range: -10.6585

Max Act: 10.2417. Min Act: -0.0000

Data Index: 809088 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.9906. Min Act: -0.0000

Data Index: 1566378 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 10.6585. Min Range: -10.6585

Max Act: 10.3632. Min Act: -0.0000

Data Index: 1382972 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 10.6585. Min Range: -10.6585

Max Act: 10.0871. Min Act: -0.0000

Data Index: 575028 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 10.6585. Min Range: -10.6585

Max Act: 10.1215. Min Act: -0.0000

Data Index: 1305959 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.7155. Min Act: -0.0000

Data Index: 1350454 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.9549. Min Act: -0.0000

Data Index: 1728717 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.5621. Min Act: -0.0000

Data Index: 473147 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.9484. Min Act: -0.0000

Data Index: 849786 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.9019. Min Act: -0.0000

Data Index: 609481 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.4933. Min Act: -0.0000

Data Index: 1398061 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 10.6585. Min Range: -10.6585

Max Act: 8.9710. Min Act: -0.0000

Data Index: 687732 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.6931. Min Act: -0.0000

Data Index: 1655709 (The Pile)

Max Activating Token Index: 902

Text #15

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.5494. Min Act: -0.0000

Data Index: 1191753 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.4029. Min Act: -0.0000

Data Index: 1717961 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 10.6585. Min Range: -10.6585

Max Act: 8.9650. Min Act: -0.0000

Data Index: 1492760 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.5162. Min Act: -0.0000

Data Index: 1979185 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 10.6585. Min Range: -10.6585

Max Act: 9.3568. Min Act: -0.0000

Data Index: 1927990 (The Pile)

Max Activating Token Index: 134