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

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

Neuron 816 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1246. Min Act: -0.0004

Data Index: 207490 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1208. Min Act: -0.0004

Data Index: 463430 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1165. Min Act: -0.0004

Data Index: 1074384 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1276. Min Act: -0.0004

Data Index: 97242 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1249. Min Act: -0.0004

Data Index: 636090 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1161. Min Act: -0.0004

Data Index: 760259 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1180. Min Act: -0.0004

Data Index: 734116 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1217. Min Act: -0.0004

Data Index: 242637 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1357. Min Act: -0.0004

Data Index: 408095 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1078. Min Act: -0.0004

Data Index: 1232169 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1060. Min Act: -0.0004

Data Index: 841127 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1176. Min Act: -0.0004

Data Index: 779689 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1132. Min Act: -0.0004

Data Index: 928066 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1084. Min Act: -0.0004

Data Index: 556041 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1051. Min Act: -0.0004

Data Index: 261121 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1091. Min Act: -0.0004

Data Index: 860200 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1107. Min Act: -0.0004

Data Index: 1070900 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1183. Min Act: -0.0004

Data Index: 677404 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0981. Min Act: -0.0004

Data Index: 1119108 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1010. Min Act: -0.0004

Data Index: 598139 (C4 (Web Text))

Max Activating Token Index: 956