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

Dataset: The Pile

Neuron 2183 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: 0.6332. Min Range: -0.6332

Max Act: 0.6332. Min Act: -0.0000

Data Index: 994950 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1274058 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1136718 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3889. Min Act: -0.0000

Data Index: 946558 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4311. Min Act: -0.0000

Data Index: 372320 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1674015 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1605705 (The Pile)

Max Activating Token Index: 741

Text #7

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1044867 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4033. Min Act: -0.0000

Data Index: 472137 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.4040. Min Act: -0.0000

Data Index: 689454 (The Pile)

Max Activating Token Index: 467

Text #10

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3604. Min Act: -0.0000

Data Index: 597454 (The Pile)

Max Activating Token Index: 945

Text #11

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3570. Min Act: -0.0000

Data Index: 212508 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1706804 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3591. Min Act: -0.0000

Data Index: 584163 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1153809 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3519. Min Act: -0.0000

Data Index: 651756 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1338363 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1934756 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1518776 (The Pile)

Max Activating Token Index: 164

Text #19

Max Range: 0.6332. Min Range: -0.6332

Max Act: 0.3366. Min Act: -0.0000

Data Index: 392648 (The Pile)

Max Activating Token Index: 100