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

Dataset: The Pile

Neuron 2055 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1497014 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1035693 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1703911 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1652548 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.5604. Min Act: -0.0000

Data Index: 551979 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1605262 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4997. Min Act: -0.0000

Data Index: 259220 (The Pile)

Max Activating Token Index: 894

Text #7

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1650250 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1227879 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1771889 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1200407 (The Pile)

Max Activating Token Index: 598

Text #11

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4506. Min Act: -0.0000

Data Index: 179346 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.3790. Min Act: -0.0000

Data Index: 430699 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4238. Min Act: -0.0000

Data Index: 700475 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1448846 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.3690. Min Act: -0.0000

Data Index: 165934 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1604478 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.3942. Min Act: -0.0000

Data Index: 454089 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1291653 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 0.6921. Min Range: -0.6921

Max Act: 0.3811. Min Act: 0.0001

Data Index: 381864 (The Pile)

Max Activating Token Index: 391