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

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

Neuron 3034 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2873. Min Act: -0.0001

Data Index: 1004009 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2811. Min Act: -0.0001

Data Index: 495480 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1166100 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2143. Min Act: -0.0001

Data Index: 597041 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2154. Min Act: -0.0001

Data Index: 1319290 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1648764 (Python Code)

Max Activating Token Index: 80

Text #6

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1996. Min Act: -0.0001

Data Index: 513345 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1995. Min Act: -0.0001

Data Index: 893610 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1277485 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1999. Min Act: -0.0001

Data Index: 128730 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1872. Min Act: -0.0001

Data Index: 274881 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.2175. Min Act: -0.0001

Data Index: 379962 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1846. Min Act: -0.0001

Data Index: 834908 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1966. Min Act: -0.0001

Data Index: 463366 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1052674 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1625. Min Act: -0.0001

Data Index: 1194441 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1270698 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1842. Min Act: -0.0001

Data Index: 912102 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1703. Min Act: -0.0001

Data Index: 444583 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.2873. Min Range: -0.2873

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1079998 (C4 (Web Text))

Max Activating Token Index: 790