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

Dataset: The Pile

Neuron 1961 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: 0.2373. Min Range: -0.2373

Max Act: 0.2373. Min Act: -0.0000

Data Index: 782930 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1600345 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1784. Min Act: -0.0000

Data Index: 173488 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1837. Min Act: -0.0000

Data Index: 415472 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1715. Min Act: -0.0000

Data Index: 817389 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1830. Min Act: -0.0000

Data Index: 95380 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1548. Min Act: -0.0000

Data Index: 225677 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1553. Min Act: -0.0000

Data Index: 539324 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1016695 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1516. Min Act: -0.0000

Data Index: 216200 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1564. Min Act: -0.0000

Data Index: 561540 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1554. Min Act: -0.0000

Data Index: 927211 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1427. Min Act: -0.0000

Data Index: 601492 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1282088 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1386. Min Act: -0.0000

Data Index: 169589 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1402. Min Act: -0.0000

Data Index: 57631 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1305. Min Act: -0.0000

Data Index: 447052 (The Pile)

Max Activating Token Index: 841

Text #17

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1483891 (The Pile)

Max Activating Token Index: 336

Text #18

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1671081 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1621908 (The Pile)

Max Activating Token Index: 625