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

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

Neuron 2741 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.3316. Min Act: -0.0000

Data Index: 1231770 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.1747. Min Act: -0.0001

Data Index: 411430 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.1043. Min Act: -0.0000

Data Index: 919023 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.3316. Min Range: -2.3316

Max Act: 1.9761. Min Act: -0.0000

Data Index: 1068627 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.1307. Min Act: -0.0000

Data Index: 1163225 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.1777. Min Act: -0.0000

Data Index: 1271730 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.0004. Min Act: -0.0000

Data Index: 1205457 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.0012. Min Act: -0.0001

Data Index: 417070 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.0445. Min Act: -0.0000

Data Index: 726376 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.1676. Min Act: -0.0000

Data Index: 938244 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.1131. Min Act: -0.0000

Data Index: 119570 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 2.3316. Min Range: -2.3316

Max Act: 1.9677. Min Act: -0.0000

Data Index: 512973 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.0669. Min Act: -0.0000

Data Index: 715388 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.1140. Min Act: -0.0000

Data Index: 1034085 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.0497. Min Act: -0.0000

Data Index: 760282 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.0502. Min Act: -0.0001

Data Index: 975388 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 2.3316. Min Range: -2.3316

Max Act: 1.9105. Min Act: -0.0000

Data Index: 330726 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.0278. Min Act: -0.0000

Data Index: 470089 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.0205. Min Act: -0.0000

Data Index: 43952 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 2.3316. Min Range: -2.3316

Max Act: 2.0191. Min Act: -0.0000

Data Index: 981507 (C4 (Web Text))

Max Activating Token Index: 51