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

Dataset: The Pile

Neuron 3586 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6437. Min Range: -5.6437

Max Act: 5.6437. Min Act: -0.0000

Data Index: 78760 (The Pile)

Max Activating Token Index: 838

Text #1

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.7893. Min Act: -0.0000

Data Index: 1616504 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.7771. Min Act: -0.0000

Data Index: 938622 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.7483. Min Act: -0.0000

Data Index: 1147183 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.9281. Min Act: -0.0000

Data Index: 1111602 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.8504. Min Act: -0.0000

Data Index: 1672766 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.6422. Min Act: -0.0000

Data Index: 1855508 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.6328. Min Act: -0.0000

Data Index: 1445793 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.5840. Min Act: -0.0000

Data Index: 829566 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.2753. Min Act: -0.0000

Data Index: 1361526 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.2476. Min Act: -0.0000

Data Index: 1539082 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.5381. Min Act: -0.0000

Data Index: 1960741 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.4582. Min Act: -0.0000

Data Index: 1851408 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.2729. Min Act: -0.0000

Data Index: 1775210 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.5463. Min Act: -0.0000

Data Index: 746375 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.2660. Min Act: -0.0000

Data Index: 291699 (The Pile)

Max Activating Token Index: 462

Text #16

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.2026. Min Act: -0.0000

Data Index: 185425 (The Pile)

Max Activating Token Index: 620

Text #17

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.1840. Min Act: -0.0000

Data Index: 703306 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 5.6437. Min Range: -5.6437

Max Act: 4.1483. Min Act: -0.0000

Data Index: 1928884 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 5.6437. Min Range: -5.6437

Max Act: 3.8770. Min Act: -0.0000

Data Index: 1551574 (The Pile)

Max Activating Token Index: 613