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

Dataset: The Pile

Neuron 4908 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: 1.8026. Min Range: -1.8026

Max Act: 1.8026. Min Act: -0.0000

Data Index: 1208436 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5382. Min Act: -0.0001

Data Index: 456134 (The Pile)

Max Activating Token Index: 824

Text #2

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.5836. Min Act: -0.0000

Data Index: 1584999 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4841. Min Act: -0.0000

Data Index: 747941 (The Pile)

Max Activating Token Index: 247

Text #4

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4812. Min Act: -0.0000

Data Index: 550419 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.3323. Min Act: -0.0000

Data Index: 67426 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4206. Min Act: -0.0000

Data Index: 787151 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1116154 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1187385 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1704718 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.3395. Min Act: -0.0001

Data Index: 1100394 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.3686. Min Act: -0.0000

Data Index: 481275 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.1860. Min Act: -0.0000

Data Index: 746783 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.3496. Min Act: -0.0000

Data Index: 1060147 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.2986. Min Act: -0.0000

Data Index: 782136 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.2307. Min Act: -0.0000

Data Index: 1579473 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.2716. Min Act: -0.0000

Data Index: 1069029 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1503000 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1780575 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 1.8026. Min Range: -1.8026

Max Act: 1.2807. Min Act: -0.0000

Data Index: 986360 (The Pile)

Max Activating Token Index: 36