Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3485 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.7333. Min Act: -0.0000

Data Index: 62329 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.8170. Min Act: -0.0001

Data Index: 1245280 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.4198. Min Act: -0.0001

Data Index: 1078796 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2046. Min Act: -0.0001

Data Index: 1117127 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2060. Min Act: -0.0001

Data Index: 747770 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2637. Min Act: -0.0001

Data Index: 1165464 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1809. Min Act: -0.0001

Data Index: 486726 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.2083. Min Act: -0.0001

Data Index: 842435 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1196. Min Act: -0.0001

Data Index: 165491 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1135. Min Act: -0.0001

Data Index: 925775 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1329. Min Act: -0.0001

Data Index: 776291 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1760. Min Act: -0.0001

Data Index: 438587 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1009959 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1217. Min Act: -0.0001

Data Index: 491268 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1458. Min Act: -0.0001

Data Index: 475860 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1122. Min Act: -0.0001

Data Index: 1068895 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1027. Min Act: -0.0001

Data Index: 204320 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1175. Min Act: -0.0001

Data Index: 1235497 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.1698. Min Act: -0.0001

Data Index: 150673 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.8170. Min Range: -1.8170

Max Act: 1.0688. Min Act: -0.0000

Data Index: 413037 (C4 (Web Text))

Max Activating Token Index: 798