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

Dataset: The Pile

Neuron 2052 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: 1.1546. Min Range: -1.1546

Max Act: 1.1011. Min Act: -0.0000

Data Index: 796955 (The Pile)

Max Activating Token Index: 371

Text #1

Max Range: 1.1546. Min Range: -1.1546

Max Act: 1.1442. Min Act: -0.0000

Data Index: 831792 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 1.1546. Min Range: -1.1546

Max Act: 1.1357. Min Act: -0.0000

Data Index: 317085 (The Pile)

Max Activating Token Index: 390

Text #3

Max Range: 1.1546. Min Range: -1.1546

Max Act: 1.0985. Min Act: -0.0000

Data Index: 412993 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.1546. Min Range: -1.1546

Max Act: 1.1546. Min Act: -0.0000

Data Index: 1764887 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1078382 (The Pile)

Max Activating Token Index: 171

Text #6

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.9498. Min Act: -0.0000

Data Index: 502965 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 1.1546. Min Range: -1.1546

Max Act: 1.0387. Min Act: -0.0000

Data Index: 840523 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1455272 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.9234. Min Act: -0.0000

Data Index: 63270 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1721853 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1474000 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1032906 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.9020. Min Act: -0.0000

Data Index: 917272 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1779697 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.9343. Min Act: -0.0000

Data Index: 917186 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.8708. Min Act: -0.0000

Data Index: 73485 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.8939. Min Act: -0.0000

Data Index: 78552 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1199545 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 1.1546. Min Range: -1.1546

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1821038 (The Pile)

Max Activating Token Index: 404