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

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

Neuron 3016 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1124582 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1131. Min Act: -0.0000

Data Index: 564563 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1379717 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1529004 (Python Code)

Max Activating Token Index: 712

Text #4

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1415763 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0977. Min Act: -0.0001

Data Index: 809348 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1588347 (Python Code)

Max Activating Token Index: 714

Text #7

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1375850 (Python Code)

Max Activating Token Index: 729

Text #8

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1414499 (Python Code)

Max Activating Token Index: 640

Text #9

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1643570 (Python Code)

Max Activating Token Index: 101

Text #10

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1627209 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0925. Min Act: -0.0000

Data Index: 729498 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1587190 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0906. Min Act: -0.0000

Data Index: 766692 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0783. Min Act: -0.0000

Data Index: 620197 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1172061 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1321702 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0786. Min Act: -0.0000

Data Index: 835825 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1179584 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1576823 (Python Code)

Max Activating Token Index: 330