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

Dataset: The Pile

Neuron 3674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0247. Min Range: -1.0247

Max Act: 1.0114. Min Act: -0.0000

Data Index: 893222 (The Pile)

Max Activating Token Index: 303

Text #1

Max Range: 1.0247. Min Range: -1.0247

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1697689 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 1.0247. Min Range: -1.0247

Max Act: 1.0105. Min Act: -0.0000

Data Index: 975572 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 1.0247. Min Range: -1.0247

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1048735 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9521. Min Act: -0.0000

Data Index: 650251 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1928705 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9270. Min Act: -0.0000

Data Index: 816065 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9390. Min Act: -0.0000

Data Index: 100374 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8599. Min Act: -0.0000

Data Index: 268392 (The Pile)

Max Activating Token Index: 399

Text #9

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1359814 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8286. Min Act: -0.0000

Data Index: 544911 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1175724 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8237. Min Act: -0.0000

Data Index: 459881 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1188007 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1329182 (The Pile)

Max Activating Token Index: 457

Text #15

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1102911 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1911310 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1410702 (The Pile)

Max Activating Token Index: 66

Text #18

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8060. Min Act: -0.0000

Data Index: 739553 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1387471 (The Pile)

Max Activating Token Index: 172