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

Dataset: The Pile

Neuron 2347 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: 2.1007. Min Range: -2.1007

Max Act: 2.1007. Min Act: -0.0000

Data Index: 1185059 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.5704. Min Act: -0.0000

Data Index: 74679 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.6328. Min Act: -0.0000

Data Index: 691543 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1820175 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.3724. Min Act: -0.0000

Data Index: 757163 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1421471 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1489435 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1792544 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1949384 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.5042. Min Act: -0.0000

Data Index: 708834 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1933780 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.1908. Min Act: -0.0000

Data Index: 623911 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.3568. Min Act: -0.0000

Data Index: 1853749 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.1576. Min Act: -0.0000

Data Index: 1563476 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.4684. Min Act: -0.0000

Data Index: 791639 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.1883. Min Act: -0.0000

Data Index: 168132 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.1872. Min Act: -0.0000

Data Index: 824173 (The Pile)

Max Activating Token Index: 487

Text #17

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1265113 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.3649. Min Act: -0.0000

Data Index: 613517 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 2.1007. Min Range: -2.1007

Max Act: 1.2099. Min Act: -0.0000

Data Index: 38344 (The Pile)

Max Activating Token Index: 981