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

Dataset: The Pile

Neuron 3171 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: 0.4963. Min Range: -0.4963

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1609796 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1695028 (The Pile)

Max Activating Token Index: 338

Text #2

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1524824 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1393087 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1010166 (The Pile)

Max Activating Token Index: 835

Text #5

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1379581 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3689. Min Act: -0.0000

Data Index: 929324 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1387987 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1487456 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1825715 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3976. Min Act: -0.0000

Data Index: 203882 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3581. Min Act: -0.0000

Data Index: 438992 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3653. Min Act: -0.0000

Data Index: 451055 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3430. Min Act: -0.0000

Data Index: 954753 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3821. Min Act: -0.0000

Data Index: 867880 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3820. Min Act: -0.0000

Data Index: 665860 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3679. Min Act: -0.0000

Data Index: 567104 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1489513 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1378388 (The Pile)

Max Activating Token Index: 437

Text #19

Max Range: 0.4963. Min Range: -0.4963

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1424108 (The Pile)

Max Activating Token Index: 905