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

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

Neuron 4765 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: 0.5654. Min Range: -0.5654

Max Act: 0.5654. Min Act: -0.0002

Data Index: 1333455 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5174. Min Act: -0.0002

Data Index: 355553 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5134. Min Act: -0.0002

Data Index: 507163 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5033. Min Act: -0.0002

Data Index: 404251 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5141. Min Act: -0.0002

Data Index: 1128026 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5130. Min Act: -0.0002

Data Index: 1120791 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5027. Min Act: -0.0002

Data Index: 230830 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5058. Min Act: -0.0002

Data Index: 368690 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5116. Min Act: -0.0002

Data Index: 228636 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5099. Min Act: -0.0002

Data Index: 64580 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5046. Min Act: -0.0002

Data Index: 887913 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5034. Min Act: -0.0002

Data Index: 431693 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5012. Min Act: -0.0002

Data Index: 734916 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4992. Min Act: -0.0002

Data Index: 1303247 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.5046. Min Act: -0.0002

Data Index: 712304 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4948. Min Act: -0.0002

Data Index: 251908 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4851. Min Act: -0.0002

Data Index: 675626 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4871. Min Act: -0.0002

Data Index: 1125747 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4872. Min Act: -0.0002

Data Index: 1156325 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.5654. Min Range: -0.5654

Max Act: 0.4890. Min Act: -0.0002

Data Index: 507221 (C4 (Web Text))

Max Activating Token Index: 415