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

Dataset: The Pile

Neuron 1740 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: 0.4238. Min Range: -0.4238

Max Act: 0.4238. Min Act: -0.0000

Data Index: 905312 (The Pile)

Max Activating Token Index: 802

Text #1

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1326230 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1438098 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2612. Min Act: -0.0000

Data Index: 311964 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2530. Min Act: -0.0000

Data Index: 701816 (The Pile)

Max Activating Token Index: 843

Text #5

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1718554 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2303. Min Act: -0.0000

Data Index: 114109 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1855490 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1010045 (The Pile)

Max Activating Token Index: 632

Text #9

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1895284 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2300. Min Act: -0.0000

Data Index: 74938 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2266. Min Act: -0.0000

Data Index: 189478 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2225. Min Act: -0.0000

Data Index: 347891 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1024827 (The Pile)

Max Activating Token Index: 352

Text #14

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1877. Min Act: -0.0000

Data Index: 466330 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2245. Min Act: -0.0000

Data Index: 949247 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1705007 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2043. Min Act: -0.0000

Data Index: 863706 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.2157. Min Act: -0.0000

Data Index: 10154 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 0.4238. Min Range: -0.4238

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1374400 (The Pile)

Max Activating Token Index: 487