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

Dataset: The Pile

Neuron 491 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2603. Min Act: -0.0000

Data Index: 1029819 (The Pile)

Max Activating Token Index: 857

Text #1

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2290. Min Act: -0.0000

Data Index: 1842552 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.8976. Min Act: -0.0000

Data Index: 1483151 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9995. Min Act: -0.0000

Data Index: 612597 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1737. Min Act: -0.0000

Data Index: 547990 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1215. Min Act: -0.0000

Data Index: 1830620 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1198. Min Act: -0.0000

Data Index: 593093 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1197. Min Act: -0.0000

Data Index: 1215947 (The Pile)

Max Activating Token Index: 907

Text #8

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1388. Min Act: -0.0000

Data Index: 21827 (The Pile)

Max Activating Token Index: 774

Text #9

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1204. Min Act: -0.0000

Data Index: 823595 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9676. Min Act: -0.0000

Data Index: 1151961 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2346. Min Act: -0.0000

Data Index: 1325298 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2394. Min Act: -0.0000

Data Index: 1767256 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0470. Min Act: -0.0000

Data Index: 671039 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0428. Min Act: -0.0000

Data Index: 1215265 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.8606. Min Act: -0.0000

Data Index: 1457831 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9931. Min Act: -0.0000

Data Index: 530246 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9845. Min Act: -0.0000

Data Index: 1846599 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.8363. Min Act: -0.0000

Data Index: 1134798 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9825. Min Act: -0.0000

Data Index: 228829 (The Pile)

Max Activating Token Index: 895