Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2127 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.2375. Min Act: -0.0000

Data Index: 909283 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1673980 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.8366. Min Act: -0.0000

Data Index: 41722 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0695. Min Act: -0.0000

Data Index: 458252 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7145. Min Act: -0.0000

Data Index: 465178 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.6469. Min Act: -0.0000

Data Index: 673032 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.7174. Min Act: -0.0000

Data Index: 243006 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1812934 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1941647 (The Pile)

Max Activating Token Index: 485

Text #9

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.5985. Min Act: -0.0000

Data Index: 301560 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.5937. Min Act: -0.0000

Data Index: 809692 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.6031. Min Act: -0.0000

Data Index: 132065 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.5652. Min Act: -0.0000

Data Index: 17471 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.5462. Min Act: -0.0000

Data Index: 210541 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.5029. Min Act: -0.0000

Data Index: 741300 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1443005 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1539592 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.5149. Min Act: -0.0000

Data Index: 864376 (The Pile)

Max Activating Token Index: 498

Text #18

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1445203 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.4974. Min Act: -0.0000

Data Index: 596672 (The Pile)

Max Activating Token Index: 976