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

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

Neuron 5398 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.6551. Min Act: -0.0002

Data Index: 761544 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.4870. Min Act: -0.0002

Data Index: 796368 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.5337. Min Act: -0.0002

Data Index: 1016462 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.3760. Min Act: -0.0002

Data Index: 811932 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.3272. Min Act: -0.0002

Data Index: 1268968 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2642. Min Act: -0.0002

Data Index: 313020 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2997. Min Act: -0.0002

Data Index: 1041294 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.3053. Min Act: -0.0002

Data Index: 123338 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2063. Min Act: -0.0002

Data Index: 296878 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2467. Min Act: -0.0002

Data Index: 450885 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2755. Min Act: -0.0002

Data Index: 1026575 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2459. Min Act: -0.0002

Data Index: 995364 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2411. Min Act: -0.0002

Data Index: 1271204 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2283. Min Act: -0.0002

Data Index: 1323000 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2183. Min Act: -0.0002

Data Index: 739125 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.1900. Min Act: -0.0003

Data Index: 726079 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.1600. Min Act: -0.0002

Data Index: 137789 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.1790. Min Act: -0.0002

Data Index: 1061646 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.2196. Min Act: -0.0002

Data Index: 492497 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 1.6551. Min Range: -1.6551

Max Act: 1.1896. Min Act: -0.0002

Data Index: 1193389 (C4 (Web Text))

Max Activating Token Index: 777