Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4677 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1703. Min Act: -0.0000

Data Index: 145256 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1468. Min Act: -0.0000

Data Index: 553477 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1598. Min Act: -0.0000

Data Index: 334093 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1574. Min Act: -0.0000

Data Index: 948011 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1230. Min Act: -0.0000

Data Index: 644545 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1270263 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1174. Min Act: -0.0000

Data Index: 129841 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1276. Min Act: -0.0000

Data Index: 953737 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1255. Min Act: -0.0000

Data Index: 223597 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1223. Min Act: -0.0000

Data Index: 897561 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1309357 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1152. Min Act: -0.0000

Data Index: 28563 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1143. Min Act: -0.0000

Data Index: 190329 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1147. Min Act: -0.0000

Data Index: 769244 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1502501 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1566549 (Python Code)

Max Activating Token Index: 343

Text #16

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1097. Min Act: -0.0000

Data Index: 826215 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1095. Min Act: -0.0000

Data Index: 251075 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1130. Min Act: -0.0000

Data Index: 211068 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.0832. Min Act: -0.0000

Data Index: 596285 (C4 (Web Text))

Max Activating Token Index: 363