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

Dataset: The Pile

Neuron 2575 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: 1.3561. Min Range: -1.3561

Max Act: 1.3561. Min Act: -0.0000

Data Index: 1870474 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.9270. Min Act: -0.0000

Data Index: 461337 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.8466. Min Act: -0.0000

Data Index: 898469 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.8083. Min Act: -0.0000

Data Index: 303489 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.7357. Min Act: -0.0000

Data Index: 93702 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.7353. Min Act: -0.0000

Data Index: 806922 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.7264. Min Act: -0.0001

Data Index: 609310 (The Pile)

Max Activating Token Index: 764

Text #7

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.7440. Min Act: -0.0000

Data Index: 987636 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.7397. Min Act: -0.0000

Data Index: 348634 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.7439. Min Act: -0.0000

Data Index: 758412 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1038519 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.7480. Min Act: -0.0000

Data Index: 199979 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1578999 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1968511 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1278518 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.6985. Min Act: -0.0000

Data Index: 464416 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.6495. Min Act: -0.0000

Data Index: 974312 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1469270 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1955959 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.6719. Min Act: -0.0000

Data Index: 861518 (The Pile)

Max Activating Token Index: 776