Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4028 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2765. Min Act: -0.0002

Data Index: 179323 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2765. Min Act: -0.0002

Data Index: 320577 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2804. Min Act: -0.0001

Data Index: 57630 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1990. Min Act: -0.0001

Data Index: 20244 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2927. Min Act: -0.0002

Data Index: 193550 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2298. Min Act: -0.0001

Data Index: 486793 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1701. Min Act: -0.0002

Data Index: 607086 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2132. Min Act: -0.0002

Data Index: 1308238 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1792. Min Act: -0.0002

Data Index: 1088616 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1813. Min Act: -0.0002

Data Index: 155373 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1767. Min Act: -0.0002

Data Index: 582638 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1995. Min Act: -0.0001

Data Index: 945936 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2381. Min Act: -0.0001

Data Index: 1110434 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2392. Min Act: -0.0001

Data Index: 1094646 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2260. Min Act: -0.0002

Data Index: 305301 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1845. Min Act: -0.0001

Data Index: 107991 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2013. Min Act: -0.0001

Data Index: 1235284 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1300. Min Act: -0.0002

Data Index: 701180 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.2111. Min Act: -0.0001

Data Index: 1208719 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.2927. Min Range: -1.2927

Max Act: 1.1337. Min Act: -0.0002

Data Index: 551496 (C4 (Web Text))

Max Activating Token Index: 902