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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3923 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4739. Min Range: -2.4739

Max Act: 2.4739. Min Act: -0.0000

Data Index: 147023 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 2.4739. Min Range: -2.4739

Max Act: 2.0399. Min Act: -0.0000

Data Index: 434150 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 2.4739. Min Range: -2.4739

Max Act: 2.0043. Min Act: -0.0000

Data Index: 1151162 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.7265. Min Act: -0.0000

Data Index: 959097 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.6266. Min Act: -0.0000

Data Index: 917180 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.6670. Min Act: -0.0000

Data Index: 886932 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.5484. Min Act: -0.0000

Data Index: 458782 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.5079. Min Act: -0.0000

Data Index: 940686 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.4976. Min Act: -0.0000

Data Index: 768991 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.4889. Min Act: -0.0000

Data Index: 476230 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.5541. Min Act: -0.0000

Data Index: 89326 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.4190. Min Act: -0.0000

Data Index: 794462 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.4882. Min Act: -0.0000

Data Index: 95682 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.4143. Min Act: -0.0000

Data Index: 977289 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.4193. Min Act: -0.0000

Data Index: 372011 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.4529. Min Act: -0.0000

Data Index: 64392 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.4038. Min Act: -0.0000

Data Index: 1267195 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1260101 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1328810 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 2.4739. Min Range: -2.4739

Max Act: 1.4064. Min Act: -0.0000

Data Index: 603745 (C4 (Web Text))

Max Activating Token Index: 1009