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

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

Neuron 3436 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: 1.1770. Min Range: -1.1770

Max Act: 1.1770. Min Act: -0.0000

Data Index: 134217 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9422. Min Act: -0.0000

Data Index: 845634 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 1.1770. Min Range: -1.1770

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1152505 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9419. Min Act: -0.0000

Data Index: 691934 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9272. Min Act: -0.0000

Data Index: 351559 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.9111. Min Act: -0.0000

Data Index: 781791 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8481. Min Act: -0.0000

Data Index: 966870 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1129154 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8587. Min Act: -0.0000

Data Index: 150735 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8233. Min Act: -0.0000

Data Index: 132654 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8306. Min Act: -0.0000

Data Index: 126771 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8212. Min Act: -0.0000

Data Index: 90093 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1359417 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8033. Min Act: -0.0000

Data Index: 771449 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.8163. Min Act: -0.0000

Data Index: 478025 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.7869. Min Act: -0.0000

Data Index: 153978 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1128506 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1181908 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1024502 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 1.1770. Min Range: -1.1770

Max Act: 0.7641. Min Act: -0.0000

Data Index: 634181 (C4 (Web Text))

Max Activating Token Index: 342