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

Dataset: The Pile

Neuron 5012 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: 0.4998. Min Range: -0.4998

Max Act: 0.4998. Min Act: -0.0000

Data Index: 563842 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4004. Min Act: -0.0000

Data Index: 890292 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1717586 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1843200 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1531028 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4124. Min Act: -0.0000

Data Index: 138015 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1777320 (The Pile)

Max Activating Token Index: 926

Text #7

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3702. Min Act: -0.0000

Data Index: 311449 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1575276 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1474005 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1200053 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1642167 (The Pile)

Max Activating Token Index: 782

Text #12

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1182382 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.2997. Min Act: -0.0000

Data Index: 735833 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1645572 (The Pile)

Max Activating Token Index: 337

Text #15

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1330192 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1319542 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1145240 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1981602 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1182273 (The Pile)

Max Activating Token Index: 765