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

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

Neuron 3915 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1022866 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.1259. Min Act: -0.0000

Data Index: 860317 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1251510 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.1777. Min Act: -0.0000

Data Index: 103193 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.1743. Min Act: -0.0000

Data Index: 146770 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1079028 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1107925 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.0379. Min Act: -0.0000

Data Index: 270449 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1091497 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.0051. Min Act: -0.0000

Data Index: 152804 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1314773 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.0407. Min Act: -0.0000

Data Index: 634914 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.9765. Min Act: -0.0000

Data Index: 717835 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1302907 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.1777. Min Range: -1.1777

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1141654 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.9818. Min Act: -0.0000

Data Index: 168794 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.8556. Min Act: -0.0000

Data Index: 588428 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.9691. Min Act: -0.0000

Data Index: 929354 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.9302. Min Act: -0.0000

Data Index: 932090 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.9942. Min Act: -0.0000

Data Index: 101049 (C4 (Web Text))

Max Activating Token Index: 372