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

Dataset: The Pile

Neuron 3257 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1228837 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1640070 (The Pile)

Max Activating Token Index: 841

Text #2

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1343387 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3877. Min Act: -0.0000

Data Index: 493707 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3354. Min Act: -0.0000

Data Index: 53398 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1219553 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1096139 (The Pile)

Max Activating Token Index: 999

Text #7

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3323. Min Act: -0.0000

Data Index: 190366 (The Pile)

Max Activating Token Index: 453

Text #8

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3266. Min Act: -0.0000

Data Index: 486880 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1111039 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3314. Min Act: -0.0000

Data Index: 248260 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3312. Min Act: -0.0000

Data Index: 32969 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3441. Min Act: -0.0000

Data Index: 285787 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2539. Min Act: -0.0000

Data Index: 434946 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3440. Min Act: -0.0000

Data Index: 606860 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2568. Min Act: -0.0000

Data Index: 428023 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1509123 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3075. Min Act: -0.0000

Data Index: 864049 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1542349 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3446. Min Act: -0.0000

Data Index: 496774 (The Pile)

Max Activating Token Index: 1012