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

Dataset: The Pile

Neuron 4472 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2493. Min Range: -1.2493

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1187780 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1426248 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1902293 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1253675 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7249. Min Act: -0.0000

Data Index: 345000 (The Pile)

Max Activating Token Index: 178

Text #5

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1232737 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7328. Min Act: -0.0000

Data Index: 397664 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1518405 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1801743 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6916. Min Act: -0.0000

Data Index: 689869 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1167398 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1439701 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.7047. Min Act: -0.0000

Data Index: 711224 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6795. Min Act: -0.0000

Data Index: 442243 (The Pile)

Max Activating Token Index: 10

Text #14

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6192. Min Act: -0.0000

Data Index: 993502 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6326. Min Act: -0.0000

Data Index: 969647 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6465. Min Act: -0.0000

Data Index: 820985 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6411. Min Act: -0.0000

Data Index: 209296 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6368. Min Act: -0.0000

Data Index: 196113 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 1.2493. Min Range: -1.2493

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1005029 (The Pile)

Max Activating Token Index: 527