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

Dataset: The Pile

Neuron 695 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: 1.9564. Min Range: -1.9564

Max Act: 1.9564. Min Act: -0.0000

Data Index: 1505911 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.6490. Min Act: -0.0000

Data Index: 1893156 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.7634. Min Act: -0.0000

Data Index: 1752095 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.7601. Min Act: -0.0000

Data Index: 1384490 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5735. Min Act: -0.0000

Data Index: 1979317 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.6985. Min Act: -0.0000

Data Index: 598149 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4443. Min Act: -0.0000

Data Index: 1936285 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5657. Min Act: -0.0000

Data Index: 1213590 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4942. Min Act: -0.0000

Data Index: 998527 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1491259 (The Pile)

Max Activating Token Index: 969

Text #10

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4830. Min Act: -0.0000

Data Index: 453210 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5408. Min Act: -0.0000

Data Index: 1101226 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5840. Min Act: -0.0000

Data Index: 891466 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4774. Min Act: -0.0000

Data Index: 624547 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.3689. Min Act: -0.0000

Data Index: 1267981 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1468145 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4524. Min Act: -0.0000

Data Index: 716361 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.3921. Min Act: -0.0000

Data Index: 512033 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1819468 (The Pile)

Max Activating Token Index: 576

Text #19

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.3389. Min Act: -0.0000

Data Index: 1378280 (The Pile)

Max Activating Token Index: 829