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

Dataset: The Pile

Neuron 3425 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: 3.1748. Min Range: -3.1748

Max Act: 3.1748. Min Act: -0.0000

Data Index: 299318 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 3.1748. Min Range: -3.1748

Max Act: 3.0164. Min Act: -0.0000

Data Index: 814608 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.7940. Min Act: -0.0000

Data Index: 117040 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.7346. Min Act: -0.0000

Data Index: 395661 (The Pile)

Max Activating Token Index: 247

Text #4

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.7129. Min Act: -0.0000

Data Index: 1168200 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.7009. Min Act: -0.0000

Data Index: 1432404 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.6745. Min Act: -0.0000

Data Index: 620500 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.6654. Min Act: -0.0000

Data Index: 697753 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.5295. Min Act: -0.0000

Data Index: 952706 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.6255. Min Act: -0.0000

Data Index: 582329 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.5341. Min Act: -0.0000

Data Index: 1602409 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.6040. Min Act: -0.0000

Data Index: 1778046 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.4706. Min Act: -0.0000

Data Index: 1035746 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.4172. Min Act: -0.0000

Data Index: 1683563 (The Pile)

Max Activating Token Index: 378

Text #14

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.2815. Min Act: -0.0000

Data Index: 1178964 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.4680. Min Act: -0.0000

Data Index: 1919139 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.3471. Min Act: -0.0000

Data Index: 493264 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.4656. Min Act: -0.0000

Data Index: 1114467 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.3353. Min Act: -0.0000

Data Index: 1300856 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.4472. Min Act: -0.0000

Data Index: 393403 (The Pile)

Max Activating Token Index: 90