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

Dataset: The Pile

Neuron 4329 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.7433. Min Act: -0.0000

Data Index: 663818 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.3772. Min Act: -0.0000

Data Index: 253993 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.1311. Min Act: -0.0000

Data Index: 1117558 (The Pile)

Max Activating Token Index: 695

Text #3

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.0484. Min Act: -0.0000

Data Index: 942621 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.3495. Min Act: -0.0000

Data Index: 787809 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.0408. Min Act: -0.0000

Data Index: 687158 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.7881. Min Act: -0.0000

Data Index: 827532 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 3.7433. Min Range: -3.7433

Max Act: 3.0532. Min Act: -0.0000

Data Index: 707820 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.6084. Min Act: -0.0000

Data Index: 1573986 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.8467. Min Act: -0.0000

Data Index: 221116 (The Pile)

Max Activating Token Index: 481

Text #10

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.5129. Min Act: -0.0000

Data Index: 247778 (The Pile)

Max Activating Token Index: 793

Text #11

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.6144. Min Act: -0.0000

Data Index: 204775 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.7229. Min Act: -0.0000

Data Index: 1878721 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.4843. Min Act: -0.0000

Data Index: 1054853 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.4633. Min Act: -0.0000

Data Index: 1759087 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.5598. Min Act: -0.0000

Data Index: 1583526 (The Pile)

Max Activating Token Index: 662

Text #16

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.2865. Min Act: -0.0000

Data Index: 1236410 (The Pile)

Max Activating Token Index: 897

Text #17

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.4889. Min Act: -0.0000

Data Index: 1624163 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.5414. Min Act: -0.0000

Data Index: 306773 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 3.7433. Min Range: -3.7433

Max Act: 2.5110. Min Act: -0.0000

Data Index: 209493 (The Pile)

Max Activating Token Index: 105