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

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

Neuron 1007 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: 2.5813. Min Range: -2.5813

Max Act: 2.5636. Min Act: -0.0000

Data Index: 1224966 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.5813. Min Act: -0.0000

Data Index: 1163009 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.1003. Min Act: -0.0000

Data Index: 101015 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.4196. Min Act: -0.0000

Data Index: 1009858 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.3969. Min Act: -0.0000

Data Index: 808369 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.2024. Min Act: -0.0000

Data Index: 1387697 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.3162. Min Act: -0.0000

Data Index: 441727 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.4287. Min Act: -0.0000

Data Index: 549554 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.1010. Min Act: -0.0000

Data Index: 1289395 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.0681. Min Act: -0.0000

Data Index: 1063628 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.0316. Min Act: -0.0000

Data Index: 509394 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 2.5813. Min Range: -2.5813

Max Act: 1.9747. Min Act: -0.0000

Data Index: 1388044 (Python Code)

Max Activating Token Index: 853

Text #12

Max Range: 2.5813. Min Range: -2.5813

Max Act: 1.9889. Min Act: -0.0000

Data Index: 414978 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 2.5813. Min Range: -2.5813

Max Act: 1.9646. Min Act: -0.0000

Data Index: 660531 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 2.5813. Min Range: -2.5813

Max Act: 1.8095. Min Act: -0.0000

Data Index: 38347 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 2.5813. Min Range: -2.5813

Max Act: 1.9532. Min Act: -0.0000

Data Index: 716677 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 2.5813. Min Range: -2.5813

Max Act: 2.0581. Min Act: -0.0000

Data Index: 730491 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 2.5813. Min Range: -2.5813

Max Act: 1.8376. Min Act: -0.0000

Data Index: 1560595 (Python Code)

Max Activating Token Index: 835

Text #18

Max Range: 2.5813. Min Range: -2.5813

Max Act: 1.9992. Min Act: -0.0000

Data Index: 1492690 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 2.5813. Min Range: -2.5813

Max Act: 1.8778. Min Act: -0.0000

Data Index: 1504554 (Python Code)

Max Activating Token Index: 26