Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2016 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1143. Min Act: -0.0003

Data Index: 931916 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1223. Min Act: -0.0003

Data Index: 49687 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1147. Min Act: -0.0003

Data Index: 1330238 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1179. Min Act: -0.0003

Data Index: 171892 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1188. Min Act: -0.0003

Data Index: 964307 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1217. Min Act: -0.0003

Data Index: 48784 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1175. Min Act: -0.0003

Data Index: 523215 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1079. Min Act: -0.0003

Data Index: 1099158 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1116. Min Act: -0.0003

Data Index: 998904 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1059. Min Act: -0.0003

Data Index: 922899 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1101. Min Act: -0.0003

Data Index: 1227884 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.0998. Min Act: -0.0003

Data Index: 116237 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1105. Min Act: -0.0003

Data Index: 384551 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1088. Min Act: -0.0003

Data Index: 504447 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1051. Min Act: -0.0003

Data Index: 648759 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1082. Min Act: -0.0003

Data Index: 639632 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1157. Min Act: -0.0003

Data Index: 1271251 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1119. Min Act: -0.0003

Data Index: 639766 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1119. Min Act: -0.0003

Data Index: 84602 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.1223. Min Range: -0.1223

Max Act: 0.1028. Min Act: -0.0003

Data Index: 443307 (C4 (Web Text))

Max Activating Token Index: 541