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

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

Neuron 1995 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: 1.3297. Min Range: -1.3297

Max Act: 1.3297. Min Act: -0.0000

Data Index: 81602 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9872. Min Act: -0.0000

Data Index: 873590 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9559. Min Act: -0.0000

Data Index: 714325 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9119. Min Act: -0.0000

Data Index: 379634 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.9112. Min Act: -0.0000

Data Index: 3740 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7773. Min Act: -0.0000

Data Index: 424267 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8472. Min Act: -0.0001

Data Index: 960247 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8331. Min Act: -0.0000

Data Index: 73646 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1078161 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1093006 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8136. Min Act: -0.0000

Data Index: 73766 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1013776 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1143593 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7944. Min Act: -0.0000

Data Index: 581395 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7630. Min Act: -0.0000

Data Index: 607783 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7264. Min Act: -0.0000

Data Index: 331989 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.8046. Min Act: -0.0000

Data Index: 100839 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1061387 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7194. Min Act: -0.0000

Data Index: 211108 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.3297. Min Range: -1.3297

Max Act: 0.7243. Min Act: -0.0000

Data Index: 527611 (C4 (Web Text))

Max Activating Token Index: 74