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

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

Neuron 4231 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3884. Min Range: -2.3884

Max Act: 2.3884. Min Act: -0.0000

Data Index: 287526 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 2.3884. Min Range: -2.3884

Max Act: 2.3104. Min Act: -0.0000

Data Index: 1239157 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.6536. Min Act: -0.0000

Data Index: 1240566 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.4118. Min Act: -0.0000

Data Index: 893060 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.4522. Min Act: -0.0000

Data Index: 586219 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.5100. Min Act: -0.0000

Data Index: 1219726 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.4799. Min Act: -0.0000

Data Index: 148823 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.3307. Min Act: -0.0000

Data Index: 314918 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.3402. Min Act: -0.0000

Data Index: 866442 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.4186. Min Act: -0.0000

Data Index: 72709 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1166904 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.3412. Min Act: -0.0000

Data Index: 280935 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.2365. Min Act: -0.0000

Data Index: 816708 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.2622. Min Act: -0.0000

Data Index: 508077 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.2119. Min Act: -0.0000

Data Index: 175157 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1186096 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.0994. Min Act: -0.0000

Data Index: 901256 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.2670. Min Act: -0.0000

Data Index: 187527 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.1727. Min Act: -0.0000

Data Index: 1151780 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 2.3884. Min Range: -2.3884

Max Act: 1.2573. Min Act: -0.0000

Data Index: 1076284 (C4 (Web Text))

Max Activating Token Index: 193