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

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

Neuron 4514 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8286. Min Range: -6.8286

Max Act: 6.8286. Min Act: -0.0000

Data Index: 218855 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 6.8286. Min Range: -6.8286

Max Act: 6.1736. Min Act: -0.0000

Data Index: 26649 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 6.8286. Min Range: -6.8286

Max Act: 5.8408. Min Act: -0.0000

Data Index: 1290771 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 6.8286. Min Range: -6.8286

Max Act: 5.4551. Min Act: -0.0000

Data Index: 118534 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 6.8286. Min Range: -6.8286

Max Act: 5.3733. Min Act: -0.0000

Data Index: 897992 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 6.8286. Min Range: -6.8286

Max Act: 5.5556. Min Act: -0.0000

Data Index: 1139242 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 6.8286. Min Range: -6.8286

Max Act: 5.1410. Min Act: -0.0000

Data Index: 217720 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 6.8286. Min Range: -6.8286

Max Act: 4.3151. Min Act: -0.0000

Data Index: 835024 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.7174. Min Act: -0.0000

Data Index: 1349308 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.8941. Min Act: -0.0000

Data Index: 431614 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.6246. Min Act: -0.0000

Data Index: 1065896 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.3622. Min Act: -0.0000

Data Index: 708483 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.2501. Min Act: -0.0000

Data Index: 475849 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.2636. Min Act: -0.0000

Data Index: 371011 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.2207. Min Act: -0.0000

Data Index: 202408 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.1081. Min Act: -0.0000

Data Index: 1266911 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.0458. Min Act: -0.0000

Data Index: 1348932 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 6.8286. Min Range: -6.8286

Max Act: 3.3151. Min Act: -0.0000

Data Index: 507485 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 6.8286. Min Range: -6.8286

Max Act: 2.8982. Min Act: -0.0000

Data Index: 414977 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 6.8286. Min Range: -6.8286

Max Act: 2.7664. Min Act: -0.0000

Data Index: 1125015 (C4 (Web Text))

Max Activating Token Index: 887