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

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

Neuron 3828 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0001

Data Index: 218123 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1243237 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0001

Data Index: 357733 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0002

Data Index: 926300 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0001

Data Index: 809192 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0150. Min Act: -0.0002

Data Index: 909334 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0138. Min Act: -0.0001

Data Index: 297986 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0098. Min Act: -0.0001

Data Index: 1250484 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0121. Min Act: -0.0001

Data Index: 342175 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0123. Min Act: -0.0001

Data Index: 654727 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0095. Min Act: -0.0001

Data Index: 1095607 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0119. Min Act: -0.0001

Data Index: 1128778 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0115. Min Act: -0.0001

Data Index: 338896 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0103. Min Act: -0.0001

Data Index: 793334 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0123. Min Act: -0.0001

Data Index: 804644 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0112. Min Act: -0.0001

Data Index: 85746 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0113. Min Act: -0.0001

Data Index: 404703 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0118. Min Act: -0.0001

Data Index: 1469249 (Python Code)

Max Activating Token Index: 265

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0113. Min Act: -0.0001

Data Index: 524143 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0086. Min Act: -0.0001

Data Index: 47854 (C4 (Web Text))

Max Activating Token Index: 462