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

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

Neuron 3143 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.2047. Min Act: -0.0001

Data Index: 461844 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9849. Min Act: -0.0001

Data Index: 927144 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9802. Min Act: -0.0001

Data Index: 44643 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9665. Min Act: -0.0001

Data Index: 12071 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8725. Min Act: -0.0001

Data Index: 1189335 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8502. Min Act: -0.0001

Data Index: 1053434 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8692. Min Act: -0.0001

Data Index: 1347724 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8512. Min Act: -0.0001

Data Index: 125980 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8341. Min Act: -0.0001

Data Index: 215129 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8333. Min Act: -0.0001

Data Index: 1088248 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7818. Min Act: -0.0001

Data Index: 864455 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8089. Min Act: -0.0001

Data Index: 234821 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8002. Min Act: -0.0001

Data Index: 1120907 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8275. Min Act: -0.0001

Data Index: 868241 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7904. Min Act: -0.0001

Data Index: 297939 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7868. Min Act: -0.0001

Data Index: 45647 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7868. Min Act: -0.0001

Data Index: 189190 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7466. Min Act: -0.0001

Data Index: 311242 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7900. Min Act: -0.0001

Data Index: 631149 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7309. Min Act: -0.0001

Data Index: 296545 (C4 (Web Text))

Max Activating Token Index: 633