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

Dataset: The Pile

Neuron 4598 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: 1.8890. Min Range: -1.8890

Max Act: 1.8046. Min Act: -0.0000

Data Index: 198690 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.8890. Min Act: -0.0000

Data Index: 1714769 (The Pile)

Max Activating Token Index: 270

Text #2

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.1540. Min Act: -0.0000

Data Index: 713169 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.3783. Min Act: -0.0000

Data Index: 1552856 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.3573. Min Act: -0.0000

Data Index: 791521 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1689335 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.1979. Min Act: -0.0000

Data Index: 779538 (The Pile)

Max Activating Token Index: 625

Text #7

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1358200 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.3779. Min Act: -0.0000

Data Index: 674257 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1597925 (The Pile)

Max Activating Token Index: 848

Text #10

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.1522. Min Act: -0.0000

Data Index: 356572 (The Pile)

Max Activating Token Index: 11

Text #11

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.0810. Min Act: -0.0000

Data Index: 252967 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 1.8890. Min Range: -1.8890

Max Act: 0.9209. Min Act: -0.0000

Data Index: 575667 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.0370. Min Act: -0.0000

Data Index: 26306 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1800516 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 1.8890. Min Range: -1.8890

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1513238 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.1256. Min Act: -0.0000

Data Index: 439514 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.1321. Min Act: -0.0000

Data Index: 1960673 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 1.8890. Min Range: -1.8890

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1149792 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 1.8890. Min Range: -1.8890

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1867651 (The Pile)

Max Activating Token Index: 554