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

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

Neuron 4854 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1344921 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4901. Min Act: -0.0000

Data Index: 125559 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.5131. Min Act: -0.0000

Data Index: 978506 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4730. Min Act: -0.0000

Data Index: 395701 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4668. Min Act: -0.0000

Data Index: 157729 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4596. Min Act: -0.0000

Data Index: 235416 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1096244 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1238044 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4168. Min Act: 0.0000

Data Index: 988261 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4147. Min Act: -0.0000

Data Index: 721438 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4189. Min Act: -0.0000

Data Index: 463653 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4212. Min Act: -0.0000

Data Index: 665260 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1166518 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3984. Min Act: -0.0000

Data Index: 903286 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4060. Min Act: 0.0000

Data Index: 673255 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4095. Min Act: -0.0000

Data Index: 563012 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3925. Min Act: -0.0000

Data Index: 686916 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1100603 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4137. Min Act: -0.0000

Data Index: 357536 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1148843 (C4 (Web Text))

Max Activating Token Index: 734