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

Dataset: The Pile

Neuron 5116 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: 3.9496. Min Range: -3.9496

Max Act: 3.9496. Min Act: -0.0000

Data Index: 1091650 (The Pile)

Max Activating Token Index: 891

Text #1

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.2016. Min Act: -0.0000

Data Index: 361430 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.5269. Min Act: -0.0000

Data Index: 1904915 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.6191. Min Act: -0.0000

Data Index: 1061653 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.3528. Min Act: -0.0000

Data Index: 787487 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.1021. Min Act: -0.0000

Data Index: 509249 (The Pile)

Max Activating Token Index: 225

Text #6

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.0896. Min Act: -0.0000

Data Index: 160288 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.6589. Min Act: -0.0000

Data Index: 472318 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.6373. Min Act: -0.0000

Data Index: 1514986 (The Pile)

Max Activating Token Index: 709

Text #9

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.0820. Min Act: -0.0000

Data Index: 1047057 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.1248. Min Act: -0.0000

Data Index: 1676004 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.0563. Min Act: -0.0000

Data Index: 48915 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.3505. Min Act: -0.0000

Data Index: 1701753 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.0051. Min Act: -0.0000

Data Index: 675402 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 3.9496. Min Range: -3.9496

Max Act: 3.0010. Min Act: -0.0000

Data Index: 891353 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 3.9496. Min Range: -3.9496

Max Act: 2.7449. Min Act: -0.0000

Data Index: 768082 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 3.9496. Min Range: -3.9496

Max Act: 2.9831. Min Act: -0.0000

Data Index: 262445 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 3.9496. Min Range: -3.9496

Max Act: 2.8392. Min Act: -0.0000

Data Index: 431105 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 3.9496. Min Range: -3.9496

Max Act: 2.9329. Min Act: -0.0000

Data Index: 250142 (The Pile)

Max Activating Token Index: 77

Text #19

Max Range: 3.9496. Min Range: -3.9496

Max Act: 2.7402. Min Act: -0.0000

Data Index: 25861 (The Pile)

Max Activating Token Index: 579