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

Dataset: The Pile

Neuron 689 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0711. Min Range: -1.0711

Max Act: 1.0377. Min Act: -0.0000

Data Index: 70940 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 1.0711. Min Range: -1.0711

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1972096 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9812. Min Act: -0.0000

Data Index: 722589 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1076245 (The Pile)

Max Activating Token Index: 831

Text #4

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1590574 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1427337 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1304729 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1325337 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1179411 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8382. Min Act: -0.0000

Data Index: 434514 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1619104 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1455696 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1738406 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1726729 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1085694 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1271920 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.7638. Min Act: -0.0000

Data Index: 21864 (The Pile)

Max Activating Token Index: 678

Text #17

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8088. Min Act: -0.0000

Data Index: 946512 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1764874 (The Pile)

Max Activating Token Index: 43

Text #19

Max Range: 1.0711. Min Range: -1.0711

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1021741 (The Pile)

Max Activating Token Index: 61