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

Dataset: The Pile

Neuron 956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.5059. Min Act: -0.0000

Data Index: 40836 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3112. Min Act: -0.0000

Data Index: 28828 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4900. Min Act: -0.0000

Data Index: 377787 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3287. Min Act: -0.0000

Data Index: 1937977 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4413. Min Act: -0.0000

Data Index: 860496 (The Pile)

Max Activating Token Index: 653

Text #5

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2295. Min Act: -0.0000

Data Index: 402720 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2968. Min Act: -0.0000

Data Index: 736470 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3261. Min Act: -0.0000

Data Index: 1041833 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3163. Min Act: -0.0000

Data Index: 241632 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3656. Min Act: -0.0000

Data Index: 1555707 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1581356 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1995495 (The Pile)

Max Activating Token Index: 31

Text #12

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2493. Min Act: -0.0000

Data Index: 405505 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2611. Min Act: -0.0000

Data Index: 434472 (The Pile)

Max Activating Token Index: 395

Text #14

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1402. Min Act: -0.0000

Data Index: 741337 (The Pile)

Max Activating Token Index: 299

Text #15

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2530. Min Act: -0.0000

Data Index: 925994 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2796. Min Act: -0.0000

Data Index: 343195 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2019. Min Act: -0.0000

Data Index: 26755 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1947. Min Act: -0.0000

Data Index: 1618819 (The Pile)

Max Activating Token Index: 549

Text #19

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2632. Min Act: -0.0000

Data Index: 1179985 (The Pile)

Max Activating Token Index: 104