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

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

Neuron 4833 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: 0.2547. Min Range: -0.2547

Max Act: 0.2402. Min Act: -0.0000

Data Index: 825593 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2547. Min Act: -0.0000

Data Index: 798011 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2403. Min Act: -0.0000

Data Index: 891507 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2352. Min Act: -0.0000

Data Index: 289716 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2161. Min Act: -0.0000

Data Index: 73481 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2134. Min Act: -0.0000

Data Index: 134270 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2199. Min Act: -0.0000

Data Index: 684447 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2008. Min Act: -0.0000

Data Index: 76375 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2010. Min Act: -0.0000

Data Index: 585783 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2048. Min Act: -0.0001

Data Index: 639235 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2239. Min Act: -0.0000

Data Index: 133393 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2004. Min Act: -0.0000

Data Index: 575434 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2117. Min Act: -0.0000

Data Index: 646333 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2032. Min Act: -0.0000

Data Index: 327361 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1979. Min Act: -0.0000

Data Index: 645849 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1328627 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1338726 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1954. Min Act: -0.0000

Data Index: 467903 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2025. Min Act: -0.0000

Data Index: 834415 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1925. Min Act: -0.0000

Data Index: 518818 (C4 (Web Text))

Max Activating Token Index: 409