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

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

Neuron 3075 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: 0.0192. Min Range: -0.0192

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1004451 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0179. Min Act: -0.0003

Data Index: 502924 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1000384 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1002638 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0137. Min Act: -0.0003

Data Index: 28140 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0141. Min Act: -0.0003

Data Index: 170068 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1269594 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1349290 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0139. Min Act: -0.0003

Data Index: 744275 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1108208 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0125. Min Act: -0.0003

Data Index: 505690 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0134. Min Act: -0.0003

Data Index: 340536 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0123. Min Act: -0.0003

Data Index: 20713 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0136. Min Act: -0.0003

Data Index: 799702 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1254333 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0126. Min Act: -0.0003

Data Index: 410107 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0126. Min Act: -0.0003

Data Index: 661214 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0123. Min Act: -0.0003

Data Index: 306652 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0123. Min Act: -0.0003

Data Index: 591763 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1014434 (C4 (Web Text))

Max Activating Token Index: 155