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

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

Neuron 3882 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1290. Min Act: -0.0001

Data Index: 317935 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1212. Min Act: -0.0001

Data Index: 836907 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1215. Min Act: -0.0001

Data Index: 561270 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1445576 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1144. Min Act: -0.0001

Data Index: 914722 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1128536 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1177. Min Act: -0.0001

Data Index: 720039 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1012533 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1234. Min Act: -0.0001

Data Index: 388650 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1195. Min Act: -0.0001

Data Index: 423383 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1103. Min Act: -0.0001

Data Index: 912737 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1112. Min Act: -0.0001

Data Index: 633717 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1084321 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1112. Min Act: -0.0001

Data Index: 803693 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1135. Min Act: -0.0001

Data Index: 987940 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1164. Min Act: -0.0001

Data Index: 103268 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1132. Min Act: -0.0001

Data Index: 960345 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1157. Min Act: -0.0001

Data Index: 87123 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1078. Min Act: -0.0001

Data Index: 430787 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1073. Min Act: -0.0001

Data Index: 747624 (C4 (Web Text))

Max Activating Token Index: 378