Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2503 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1222138 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1248. Min Act: -0.0001

Data Index: 183260 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1203. Min Act: -0.0001

Data Index: 750968 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1134. Min Act: -0.0001

Data Index: 165781 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1086. Min Act: -0.0001

Data Index: 929274 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1187. Min Act: -0.0001

Data Index: 773257 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1296947 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1123. Min Act: -0.0001

Data Index: 477395 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1103. Min Act: -0.0001

Data Index: 572439 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1436169 (Python Code)

Max Activating Token Index: 765

Text #10

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1212. Min Act: -0.0001

Data Index: 434568 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1045. Min Act: -0.0001

Data Index: 225506 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1080. Min Act: -0.0001

Data Index: 814409 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1484880 (Python Code)

Max Activating Token Index: 555

Text #14

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1393811 (Python Code)

Max Activating Token Index: 682

Text #15

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1020. Min Act: -0.0001

Data Index: 1282558 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1017. Min Act: -0.0001

Data Index: 691855 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1581380 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.0973. Min Act: -0.0001

Data Index: 549549 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.1248. Min Range: -0.1248

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1112143 (C4 (Web Text))

Max Activating Token Index: 108