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

Dataset: The Pile

Neuron 1977 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.9240. Min Act: -0.0000

Data Index: 1372913 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8793. Min Act: -0.0000

Data Index: 1024423 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.8509. Min Act: -0.0000

Data Index: 1186184 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.6160. Min Act: 0.0000

Data Index: 1655239 (The Pile)

Max Activating Token Index: 318

Text #4

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.7491. Min Act: 0.0000

Data Index: 636153 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.5846. Min Act: -0.0000

Data Index: 1389988 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.5575. Min Act: -0.0000

Data Index: 1085056 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.4934. Min Act: -0.0000

Data Index: 1230950 (The Pile)

Max Activating Token Index: 453

Text #8

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.0374. Min Act: -0.0000

Data Index: 1040895 (The Pile)

Max Activating Token Index: 533

Text #9

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.1590. Min Act: -0.0000

Data Index: 986296 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.6342. Min Act: -0.0000

Data Index: 260832 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.2842. Min Act: 0.0000

Data Index: 1195327 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.9131. Min Act: -0.0000

Data Index: 1570102 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.1765. Min Act: 0.0000

Data Index: 168866 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.1685. Min Act: -0.0000

Data Index: 884232 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.1410. Min Act: -0.0000

Data Index: 1850732 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.0159. Min Act: 0.0000

Data Index: 558305 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.0673. Min Act: 0.0000

Data Index: 1084599 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 3.9240. Min Range: -3.9240

Max Act: 3.1902. Min Act: -0.0000

Data Index: 835959 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 3.9240. Min Range: -3.9240

Max Act: 2.8917. Min Act: 0.0000

Data Index: 878509 (The Pile)

Max Activating Token Index: 221