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

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

Neuron 29 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1739. Min Act: -0.0001

Data Index: 1544652 (Python Code)

Max Activating Token Index: 950

Text #1

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1436. Min Act: 0.0000

Data Index: 732391 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1196256 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1525704 (Python Code)

Max Activating Token Index: 716

Text #4

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1203290 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1184. Min Act: -0.0000

Data Index: 322611 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1252. Min Act: -0.0001

Data Index: 484581 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1250. Min Act: -0.0001

Data Index: 624638 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1202. Min Act: -0.0000

Data Index: 75045 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1299009 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1229948 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1632573 (Python Code)

Max Activating Token Index: 804

Text #12

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1134. Min Act: -0.0000

Data Index: 135834 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1088815 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1172. Min Act: -0.0000

Data Index: 238107 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1150. Min Act: -0.0001

Data Index: 211322 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1207. Min Act: -0.0000

Data Index: 346635 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1207. Min Act: -0.0000

Data Index: 790298 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1551656 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1204. Min Act: -0.0001

Data Index: 634975 (C4 (Web Text))

Max Activating Token Index: 311