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

Dataset: The Pile

Neuron 4012 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: 1.7518. Min Range: -1.7518

Max Act: 1.7518. Min Act: -0.0000

Data Index: 700945 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.4764. Min Act: -0.0000

Data Index: 1887498 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1996958 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1704105 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1870431 (The Pile)

Max Activating Token Index: 835

Text #5

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.2937. Min Act: -0.0000

Data Index: 228513 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.4452. Min Act: -0.0000

Data Index: 1554320 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.2658. Min Act: -0.0000

Data Index: 462575 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.4135. Min Act: -0.0000

Data Index: 1498386 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.3594. Min Act: -0.0000

Data Index: 327521 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.3345. Min Act: -0.0000

Data Index: 1885419 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1396209 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1342776 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1946587 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.1924. Min Act: -0.0000

Data Index: 173213 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1690956 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1321301 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1521982 (The Pile)

Max Activating Token Index: 608

Text #18

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.2800. Min Act: -0.0000

Data Index: 1149467 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.1557. Min Act: -0.0000

Data Index: 112292 (The Pile)

Max Activating Token Index: 576