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

Dataset: The Pile

Neuron 4117 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.7375. Min Act: -0.0000

Data Index: 60718 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.8044. Min Act: -0.0000

Data Index: 1553998 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.9972. Min Act: -0.0000

Data Index: 1218916 (The Pile)

Max Activating Token Index: 129

Text #3

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.8179. Min Act: -0.0000

Data Index: 92236 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1172366 (The Pile)

Max Activating Token Index: 503

Text #5

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.6794. Min Act: -0.0000

Data Index: 1845006 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.4908. Min Act: -0.0000

Data Index: 1279926 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.4289. Min Act: -0.0000

Data Index: 121242 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.5993. Min Act: -0.0000

Data Index: 1875243 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.3328. Min Act: -0.0000

Data Index: 998564 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1997981 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.4294. Min Act: -0.0000

Data Index: 436038 (The Pile)

Max Activating Token Index: 975

Text #12

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.4005. Min Act: -0.0000

Data Index: 250803 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.3843. Min Act: -0.0000

Data Index: 137557 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.3799. Min Act: -0.0000

Data Index: 1148535 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.3606. Min Act: -0.0000

Data Index: 1694914 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.1938. Min Act: -0.0000

Data Index: 88940 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.2713. Min Act: -0.0000

Data Index: 387164 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1126936 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 1.9972. Min Range: -1.9972

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1355148 (The Pile)

Max Activating Token Index: 443