Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 491 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0006

Data Index: 504358 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0006

Data Index: 167116 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0006

Data Index: 278703 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0006

Data Index: 150690 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0006

Data Index: 510466 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0006

Data Index: 289998 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1302190 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0006

Data Index: 141867 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1643290 (Python Code)

Max Activating Token Index: 767

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0006

Data Index: 705354 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1286483 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1011346 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1442261 (Python Code)

Max Activating Token Index: 607

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1272962 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0006

Data Index: 644338 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1302823 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0006

Data Index: 312068 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0006

Data Index: 232079 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1076178 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0117. Min Act: -0.0006

Data Index: 793619 (C4 (Web Text))

Max Activating Token Index: 815