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

Dataset: The Pile

Neuron 4618 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: 3.5083. Min Range: -3.5083

Max Act: 3.5083. Min Act: -0.0000

Data Index: 874938 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.2308. Min Act: -0.0000

Data Index: 340109 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.1970. Min Act: -0.0000

Data Index: 1315938 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.9512. Min Act: -0.0000

Data Index: 1299082 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.8643. Min Act: -0.0000

Data Index: 443071 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.9975. Min Act: -0.0000

Data Index: 1630520 (The Pile)

Max Activating Token Index: 370

Text #6

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.8435. Min Act: -0.0000

Data Index: 887788 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.9699. Min Act: -0.0000

Data Index: 1000118 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 3.5083. Min Range: -3.5083

Max Act: 3.0930. Min Act: -0.0000

Data Index: 1599667 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.9190. Min Act: -0.0000

Data Index: 564483 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.5628. Min Act: -0.0000

Data Index: 1639488 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.8161. Min Act: -0.0000

Data Index: 835357 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.9450. Min Act: -0.0000

Data Index: 961762 (The Pile)

Max Activating Token Index: 116

Text #13

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.6641. Min Act: -0.0000

Data Index: 624963 (The Pile)

Max Activating Token Index: 202

Text #14

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.7686. Min Act: -0.0000

Data Index: 1775375 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.6394. Min Act: -0.0000

Data Index: 472062 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.7459. Min Act: -0.0000

Data Index: 135375 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.7618. Min Act: -0.0000

Data Index: 1283456 (The Pile)

Max Activating Token Index: 928

Text #18

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.7420. Min Act: -0.0000

Data Index: 461087 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 3.5083. Min Range: -3.5083

Max Act: 2.7482. Min Act: -0.0000

Data Index: 666180 (The Pile)

Max Activating Token Index: 610