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

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

Neuron 366 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.6166. Min Act: -0.0000

Data Index: 936094 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5852. Min Act: -0.0000

Data Index: 1430109 (Python Code)

Max Activating Token Index: 688

Text #2

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1382776 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1315106 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1437915 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5554. Min Act: -0.0000

Data Index: 883566 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5293. Min Act: -0.0000

Data Index: 101326 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5056. Min Act: 0.0000

Data Index: 1029008 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5617. Min Act: 0.0000

Data Index: 1532342 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5182. Min Act: -0.0000

Data Index: 209623 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1031223 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5303. Min Act: -0.0000

Data Index: 823412 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5002. Min Act: -0.0000

Data Index: 806587 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1285224 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5172. Min Act: 0.0000

Data Index: 1383477 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4826. Min Act: -0.0000

Data Index: 141654 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1631472 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1536299 (Python Code)

Max Activating Token Index: 825

Text #18

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4780. Min Act: 0.0000

Data Index: 1359076 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4647. Min Act: -0.0000

Data Index: 399082 (C4 (Web Text))

Max Activating Token Index: 919