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

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

Neuron 4774 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2000. Min Range: -1.2000

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1156573 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.2000. Min Range: -1.2000

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1336876 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1257994 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.8290. Min Act: -0.0000

Data Index: 731244 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.7989. Min Act: -0.0000

Data Index: 20466 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.7966. Min Act: -0.0000

Data Index: 744396 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.7705. Min Act: 0.0000

Data Index: 21184 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.7569. Min Act: -0.0000

Data Index: 657857 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.8094. Min Act: -0.0000

Data Index: 663169 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1043049 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.7172. Min Act: 0.0000

Data Index: 747 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1071690 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.6992. Min Act: -0.0000

Data Index: 597194 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1193485 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1245658 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.6924. Min Act: -0.0000

Data Index: 163616 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.6618. Min Act: -0.0000

Data Index: 45733 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.6360. Min Act: -0.0000

Data Index: 611645 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.6328. Min Act: -0.0000

Data Index: 845722 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.2000. Min Range: -1.2000

Max Act: 0.5924. Min Act: -0.0000

Data Index: 685015 (C4 (Web Text))

Max Activating Token Index: 696