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

Dataset: The Pile

Neuron 1640 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: 0.4572. Min Range: -0.4572

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1276604 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4528. Min Act: -0.0000

Data Index: 479289 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1399771 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1933344 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1825820 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4229. Min Act: -0.0000

Data Index: 574290 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4088. Min Act: -0.0000

Data Index: 748767 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3970. Min Act: -0.0000

Data Index: 565755 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4053. Min Act: -0.0000

Data Index: 749068 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1991593 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4009. Min Act: -0.0000

Data Index: 80065 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4032. Min Act: -0.0000

Data Index: 413032 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1172434 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1821356 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1702993 (The Pile)

Max Activating Token Index: 878

Text #15

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1579554 (The Pile)

Max Activating Token Index: 808

Text #16

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4061. Min Act: -0.0000

Data Index: 884743 (The Pile)

Max Activating Token Index: 50

Text #17

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1092189 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3952. Min Act: -0.0000

Data Index: 823074 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3925. Min Act: -0.0000

Data Index: 405501 (The Pile)

Max Activating Token Index: 99