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

Dataset: The Pile

Neuron 78 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.5546. Min Act: -0.0000

Data Index: 962378 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4977. Min Act: -0.0000

Data Index: 152358 (The Pile)

Max Activating Token Index: 280

Text #2

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.5696. Min Act: -0.0000

Data Index: 60699 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.5532. Min Act: -0.0000

Data Index: 1884580 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4987. Min Act: -0.0000

Data Index: 1944284 (The Pile)

Max Activating Token Index: 73

Text #5

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4861. Min Act: -0.0000

Data Index: 947715 (The Pile)

Max Activating Token Index: 753

Text #6

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4730. Min Act: -0.0000

Data Index: 652498 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4877. Min Act: -0.0000

Data Index: 1937391 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.3719. Min Act: -0.0000

Data Index: 1098056 (The Pile)

Max Activating Token Index: 822

Text #9

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.3888. Min Act: -0.0000

Data Index: 534412 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4454. Min Act: -0.0000

Data Index: 782707 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1358630 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4094. Min Act: -0.0000

Data Index: 1053 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4747. Min Act: -0.0000

Data Index: 116364 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.3984. Min Act: -0.0000

Data Index: 777457 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1720644 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4211. Min Act: -0.0000

Data Index: 1233128 (The Pile)

Max Activating Token Index: 438

Text #17

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.3813. Min Act: -0.0000

Data Index: 1210192 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4458. Min Act: -0.0000

Data Index: 1105913 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.3656. Min Act: -0.0000

Data Index: 672075 (The Pile)

Max Activating Token Index: 50