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

Dataset: The Pile

Neuron 2687 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0396. Min Range: -1.0396

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1246979 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 1.0396. Min Range: -1.0396

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1301816 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1550158 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1176593 (The Pile)

Max Activating Token Index: 432

Text #4

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.9695. Min Act: -0.0000

Data Index: 243665 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1855219 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.9248. Min Act: -0.0000

Data Index: 472285 (The Pile)

Max Activating Token Index: 665

Text #7

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1999413 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8592. Min Act: -0.0000

Data Index: 102131 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1456184 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7130. Min Act: -0.0000

Data Index: 489876 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8467. Min Act: -0.0000

Data Index: 758279 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1066099 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1144319 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8101. Min Act: -0.0000

Data Index: 322510 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8149. Min Act: -0.0000

Data Index: 661606 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1341497 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7882. Min Act: -0.0000

Data Index: 858702 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1786739 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 1.0396. Min Range: -1.0396

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1225260 (The Pile)

Max Activating Token Index: 591