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

Dataset: The Pile

Neuron 3897 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1453357 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4471. Min Act: -0.0000

Data Index: 333801 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1982954 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4381. Min Act: -0.0000

Data Index: 272627 (The Pile)

Max Activating Token Index: 514

Text #4

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1838441 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4350. Min Act: -0.0000

Data Index: 4294 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4442. Min Act: -0.0000

Data Index: 403368 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1742475 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1783392 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1954426 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4046. Min Act: -0.0000

Data Index: 400342 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3705. Min Act: -0.0000

Data Index: 117003 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3761. Min Act: 0.0000

Data Index: 407390 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1154170 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3857. Min Act: -0.0000

Data Index: 120452 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1439641 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3655. Min Act: -0.0000

Data Index: 787521 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1218659 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1147002 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3773. Min Act: -0.0000

Data Index: 325030 (The Pile)

Max Activating Token Index: 143