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

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

Neuron 2019 in Layer 0

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: 0.1255. Min Range: -0.1255

Max Act: 0.1255. Min Act: -0.0001

Data Index: 513641 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1225. Min Act: -0.0002

Data Index: 1023935 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1190197 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1134. Min Act: -0.0001

Data Index: 387777 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1291585 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1046. Min Act: -0.0001

Data Index: 272775 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1071. Min Act: -0.0002

Data Index: 570463 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1034. Min Act: -0.0001

Data Index: 633317 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1030. Min Act: -0.0001

Data Index: 450398 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1022. Min Act: -0.0001

Data Index: 340856 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1031. Min Act: -0.0001

Data Index: 65333 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1026. Min Act: -0.0001

Data Index: 642154 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1157552 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1028. Min Act: -0.0001

Data Index: 720287 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1272858 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1018. Min Act: -0.0001

Data Index: 773272 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0994. Min Act: -0.0001

Data Index: 605127 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1147821 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1013. Min Act: -0.0001

Data Index: 723196 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1013. Min Act: -0.0001

Data Index: 629916 (C4 (Web Text))

Max Activating Token Index: 486