Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3449 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0130. Min Act: -0.0003

Data Index: 27655 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0129. Min Act: -0.0003

Data Index: 951505 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1343644 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0116. Min Act: -0.0003

Data Index: 175402 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0118. Min Act: -0.0003

Data Index: 187836 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0117. Min Act: -0.0003

Data Index: 273808 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0115. Min Act: -0.0003

Data Index: 238334 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0109. Min Act: -0.0003

Data Index: 983768 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0112. Min Act: -0.0003

Data Index: 28314 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0112. Min Act: -0.0003

Data Index: 244422 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0110. Min Act: -0.0003

Data Index: 388164 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0105. Min Act: -0.0003

Data Index: 623432 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1205687 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1547903 (Python Code)

Max Activating Token Index: 986

Text #14

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0104. Min Act: -0.0003

Data Index: 23274 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0101. Min Act: -0.0003

Data Index: 859393 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1014496 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0104. Min Act: -0.0003

Data Index: 394395 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0101. Min Act: -0.0003

Data Index: 795763 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.0130. Min Range: -0.0130

Max Act: 0.0101. Min Act: -0.0003

Data Index: 652569 (C4 (Web Text))

Max Activating Token Index: 331