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

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

Neuron 765 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.8595. Min Act: -0.0000

Data Index: 502689 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.7242. Min Act: -0.0000

Data Index: 943286 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.4811. Min Act: -0.0000

Data Index: 147639 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.5022. Min Act: -0.0000

Data Index: 1010586 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.5029. Min Act: -0.0000

Data Index: 322453 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.3396. Min Act: -0.0000

Data Index: 111020 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.4260. Min Act: -0.0000

Data Index: 430759 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.1520. Min Act: -0.0000

Data Index: 189910 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.1485. Min Act: -0.0000

Data Index: 167793 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.3312. Min Act: -0.0000

Data Index: 175432 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.2418. Min Act: -0.0000

Data Index: 753380 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.2394. Min Act: -0.0000

Data Index: 501917 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.2185. Min Act: -0.0000

Data Index: 851768 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.1819. Min Act: -0.0000

Data Index: 694905 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.2784. Min Act: -0.0000

Data Index: 104884 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1017208 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.1260. Min Act: -0.0000

Data Index: 574394 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.1690. Min Act: -0.0000

Data Index: 426109 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1156308 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 1.8595. Min Range: -1.8595

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1133138 (C4 (Web Text))

Max Activating Token Index: 885