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

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

Neuron 6065 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: 0.1112. Min Range: -0.1112

Max Act: 0.1112. Min Act: -0.0002

Data Index: 653678 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1089. Min Act: -0.0002

Data Index: 727594 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1047. Min Act: -0.0002

Data Index: 782709 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1004245 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1324767 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1067. Min Act: -0.0002

Data Index: 344061 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1069. Min Act: -0.0002

Data Index: 939592 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1049. Min Act: -0.0002

Data Index: 315208 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1078. Min Act: -0.0002

Data Index: 475837 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1034. Min Act: -0.0002

Data Index: 867219 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1294305 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1032. Min Act: -0.0002

Data Index: 458454 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1016. Min Act: -0.0002

Data Index: 944141 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1014. Min Act: -0.0002

Data Index: 23126 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1020. Min Act: -0.0002

Data Index: 389332 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1016. Min Act: -0.0002

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1035. Min Act: -0.0002

Data Index: 500613 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1008. Min Act: -0.0002

Data Index: 201487 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1342391 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1003. Min Act: -0.0002

Data Index: 37539 (C4 (Web Text))

Max Activating Token Index: 852