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

Dataset: The Pile

Neuron 3302 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.7451. Min Act: -0.0000

Data Index: 546714 (The Pile)

Max Activating Token Index: 809

Text #1

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1070084 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5652. Min Act: -0.0000

Data Index: 314896 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1397035 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1453060 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1372267 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5573. Min Act: -0.0000

Data Index: 4388 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1625982 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5560. Min Act: -0.0000

Data Index: 389395 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5236. Min Act: -0.0000

Data Index: 720131 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6839. Min Act: -0.0000

Data Index: 92590 (The Pile)

Max Activating Token Index: 583

Text #11

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1284346 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4495. Min Act: -0.0000

Data Index: 148182 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4755. Min Act: -0.0000

Data Index: 987114 (The Pile)

Max Activating Token Index: 394

Text #14

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1523195 (The Pile)

Max Activating Token Index: 866

Text #15

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4075. Min Act: -0.0000

Data Index: 270732 (The Pile)

Max Activating Token Index: 937

Text #16

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4995. Min Act: -0.0000

Data Index: 666941 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4917. Min Act: -0.0000

Data Index: 717887 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1343416 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1100922 (The Pile)

Max Activating Token Index: 362