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

Dataset: The Pile

Neuron 1801 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: 5.6625. Min Range: -5.6625

Max Act: 5.6625. Min Act: -0.0000

Data Index: 496503 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 5.6625. Min Range: -5.6625

Max Act: 5.2661. Min Act: -0.0000

Data Index: 536158 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 5.6625. Min Range: -5.6625

Max Act: 4.9564. Min Act: -0.0000

Data Index: 1325515 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 5.6625. Min Range: -5.6625

Max Act: 4.7445. Min Act: -0.0000

Data Index: 1691128 (The Pile)

Max Activating Token Index: 759

Text #4

Max Range: 5.6625. Min Range: -5.6625

Max Act: 4.0175. Min Act: -0.0000

Data Index: 212103 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 5.6625. Min Range: -5.6625

Max Act: 4.3298. Min Act: -0.0000

Data Index: 1140627 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 5.6625. Min Range: -5.6625

Max Act: 4.2682. Min Act: -0.0000

Data Index: 363012 (The Pile)

Max Activating Token Index: 566

Text #7

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.8314. Min Act: -0.0000

Data Index: 53389 (The Pile)

Max Activating Token Index: 905

Text #8

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.6872. Min Act: -0.0000

Data Index: 1335150 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.8296. Min Act: -0.0000

Data Index: 855007 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.5018. Min Act: -0.0000

Data Index: 1379198 (The Pile)

Max Activating Token Index: 816

Text #11

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.9160. Min Act: -0.0000

Data Index: 1931211 (The Pile)

Max Activating Token Index: 360

Text #12

Max Range: 5.6625. Min Range: -5.6625

Max Act: 4.2981. Min Act: -0.0000

Data Index: 1821587 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.4644. Min Act: -0.0000

Data Index: 1821492 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.1381. Min Act: -0.0000

Data Index: 513208 (The Pile)

Max Activating Token Index: 885

Text #15

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.7370. Min Act: -0.0000

Data Index: 279522 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.7767. Min Act: -0.0000

Data Index: 1130558 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.6556. Min Act: -0.0000

Data Index: 296869 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.4584. Min Act: -0.0000

Data Index: 1624822 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 5.6625. Min Range: -5.6625

Max Act: 3.5609. Min Act: -0.0000

Data Index: 466499 (The Pile)

Max Activating Token Index: 348