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

Dataset: The Pile

Neuron 1045 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1633. Min Act: -0.0000

Data Index: 335595 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1275032 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1624. Min Act: -0.0000

Data Index: 319341 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1450. Min Act: -0.0000

Data Index: 914987 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1443. Min Act: -0.0000

Data Index: 441542 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1207087 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1839891 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1394. Min Act: -0.0000

Data Index: 749977 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1386319 (The Pile)

Max Activating Token Index: 769

Text #9

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1790823 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1450. Min Act: -0.0000

Data Index: 257996 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1898761 (The Pile)

Max Activating Token Index: 743

Text #12

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1296. Min Act: -0.0000

Data Index: 806690 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1898194 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1324. Min Act: -0.0000

Data Index: 394627 (The Pile)

Max Activating Token Index: 829

Text #15

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1600138 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1217. Min Act: -0.0000

Data Index: 905198 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1256615 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1940310 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1202. Min Act: -0.0000

Data Index: 152474 (The Pile)

Max Activating Token Index: 935