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

Dataset: The Pile

Neuron 139 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.2446. Min Act: -0.0000

Data Index: 569053 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1508670 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0903. Min Act: 0.0001

Data Index: 1360174 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0822. Min Act: -0.0000

Data Index: 91247 (The Pile)

Max Activating Token Index: 895

Text #4

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0450. Min Act: 0.0000

Data Index: 1957101 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9993. Min Act: -0.0000

Data Index: 709850 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1661497 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0276. Min Act: 0.0000

Data Index: 216693 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0108. Min Act: 0.0000

Data Index: 722565 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0128. Min Act: -0.0000

Data Index: 256853 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0597. Min Act: -0.0000

Data Index: 431753 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0652. Min Act: -0.0000

Data Index: 576068 (The Pile)

Max Activating Token Index: 512

Text #12

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0036. Min Act: -0.0000

Data Index: 149250 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9659. Min Act: -0.0000

Data Index: 7642 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9935. Min Act: -0.0000

Data Index: 137624 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0088. Min Act: 0.0000

Data Index: 1405113 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1136019 (The Pile)

Max Activating Token Index: 333

Text #17

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9677. Min Act: 0.0001

Data Index: 399302 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9814. Min Act: -0.0000

Data Index: 25613 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1222323 (The Pile)

Max Activating Token Index: 75