Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.1751. Min Range: -3.1751

Max Act: 3.1751. Min Act: -0.0000

Data Index: 1600151 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 3.1751. Min Range: -3.1751

Max Act: 3.1218. Min Act: -0.0000

Data Index: 994635 (The Pile)

Max Activating Token Index: 424

Text #2

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.6438. Min Act: -0.0000

Data Index: 1584718 (The Pile)

Max Activating Token Index: 893

Text #3

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.3371. Min Act: -0.0000

Data Index: 1648537 (The Pile)

Max Activating Token Index: 561

Text #4

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.5179. Min Act: -0.0000

Data Index: 517379 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.9931. Min Act: -0.0000

Data Index: 36464 (The Pile)

Max Activating Token Index: 910

Text #6

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.0007. Min Act: -0.0000

Data Index: 1029637 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.0729. Min Act: -0.0000

Data Index: 12751 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.0380. Min Act: -0.0000

Data Index: 831729 (The Pile)

Max Activating Token Index: 384

Text #9

Max Range: 3.1751. Min Range: -3.1751

Max Act: 2.1512. Min Act: -0.0000

Data Index: 847 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.9657. Min Act: -0.0000

Data Index: 1946972 (The Pile)

Max Activating Token Index: 828

Text #11

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.9719. Min Act: -0.0000

Data Index: 511884 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.9609. Min Act: -0.0000

Data Index: 774401 (The Pile)

Max Activating Token Index: 708

Text #13

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.9537. Min Act: -0.0000

Data Index: 1149577 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.8950. Min Act: -0.0001

Data Index: 1354919 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.8940. Min Act: -0.0000

Data Index: 1695614 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.8555. Min Act: -0.0000

Data Index: 718465 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.8366. Min Act: -0.0000

Data Index: 49642 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.7272. Min Act: -0.0000

Data Index: 1310789 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 3.1751. Min Range: -3.1751

Max Act: 1.7467. Min Act: -0.0000

Data Index: 512979 (The Pile)

Max Activating Token Index: 322