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

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

Neuron 853 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5998. Min Range: -2.5998

Max Act: 2.5998. Min Act: -0.0000

Data Index: 145544 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 2.5998. Min Range: -2.5998

Max Act: 2.2164. Min Act: -0.0000

Data Index: 807513 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 2.5998. Min Range: -2.5998

Max Act: 2.0344. Min Act: -0.0000

Data Index: 435686 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.9081. Min Act: -0.0000

Data Index: 637108 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.8106. Min Act: -0.0000

Data Index: 999780 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.8157. Min Act: -0.0000

Data Index: 165208 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.8533. Min Act: -0.0000

Data Index: 1151255 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.8149. Min Act: -0.0000

Data Index: 250499 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.7224. Min Act: -0.0000

Data Index: 762209 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 2.5998. Min Range: -2.5998

Max Act: 2.0062. Min Act: -0.0000

Data Index: 1129513 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.6676. Min Act: -0.0000

Data Index: 101181 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.8549. Min Act: -0.0000

Data Index: 1206540 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1278065 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.7609. Min Act: -0.0000

Data Index: 458185 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.8347. Min Act: -0.0000

Data Index: 56191 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.7260. Min Act: -0.0000

Data Index: 477044 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.7294. Min Act: -0.0000

Data Index: 433722 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.7887. Min Act: -0.0000

Data Index: 392755 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.7839. Min Act: -0.0000

Data Index: 696837 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 2.5998. Min Range: -2.5998

Max Act: 1.8985. Min Act: -0.0000

Data Index: 56624 (C4 (Web Text))

Max Activating Token Index: 538