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

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

Neuron 3423 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0003

Data Index: 613847 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0180. Min Act: -0.0003

Data Index: 371414 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0176. Min Act: -0.0003

Data Index: 535494 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0171. Min Act: -0.0003

Data Index: 344259 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0158. Min Act: -0.0002

Data Index: 907997 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0161. Min Act: -0.0003

Data Index: 607839 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1122351 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0127. Min Act: -0.0003

Data Index: 644306 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1309786 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0139. Min Act: -0.0003

Data Index: 90571 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0141. Min Act: -0.0003

Data Index: 488765 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1102596 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0133. Min Act: -0.0003

Data Index: 579030 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0133. Min Act: -0.0003

Data Index: 211022 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0126. Min Act: -0.0003

Data Index: 201609 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0125. Min Act: -0.0003

Data Index: 759400 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0128. Min Act: -0.0003

Data Index: 732080 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1307790 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0130. Min Act: -0.0003

Data Index: 154456 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0126. Min Act: -0.0003

Data Index: 713162 (C4 (Web Text))

Max Activating Token Index: 46