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

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

Neuron 4860 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: 1.6264. Min Range: -1.6264

Max Act: 1.6264. Min Act: -0.0000

Data Index: 1310417 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.3378. Min Act: -0.0000

Data Index: 252277 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.3891. Min Act: -0.0000

Data Index: 999001 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.3591. Min Act: -0.0000

Data Index: 228625 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.2834. Min Act: -0.0000

Data Index: 678769 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1260957 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.2560. Min Act: -0.0000

Data Index: 366888 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.2519. Min Act: -0.0000

Data Index: 513372 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.2360. Min Act: -0.0000

Data Index: 299077 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.1399. Min Act: -0.0000

Data Index: 423397 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.1950. Min Act: -0.0000

Data Index: 1146588 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.1075. Min Act: -0.0000

Data Index: 785886 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.1096. Min Act: -0.0000

Data Index: 185931 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.0976. Min Act: -0.0000

Data Index: 1005869 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.1572. Min Act: -0.0000

Data Index: 346707 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.0854. Min Act: -0.0000

Data Index: 908198 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1021591 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1317255 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.0746. Min Act: -0.0000

Data Index: 121983 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.6264. Min Range: -1.6264

Max Act: 1.0518. Min Act: -0.0000

Data Index: 698040 (C4 (Web Text))

Max Activating Token Index: 291