Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 499 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.4925. Min Range: -3.4925

Max Act: 3.1012. Min Act: -0.0000

Data Index: 717437 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 3.4925. Min Range: -3.4925

Max Act: 3.0608. Min Act: -0.0000

Data Index: 818272 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.9694. Min Act: -0.0000

Data Index: 1059201 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 3.4925. Min Range: -3.4925

Max Act: 3.0513. Min Act: -0.0000

Data Index: 377039 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 3.4925. Min Range: -3.4925

Max Act: 3.4925. Min Act: -0.0000

Data Index: 789723 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 3.4925. Min Range: -3.4925

Max Act: 3.0016. Min Act: -0.0000

Data Index: 451646 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.8739. Min Act: -0.0000

Data Index: 394335 (The Pile)

Max Activating Token Index: 438

Text #7

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.6986. Min Act: -0.0000

Data Index: 304366 (The Pile)

Max Activating Token Index: 792

Text #8

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.7765. Min Act: -0.0000

Data Index: 627969 (The Pile)

Max Activating Token Index: 571

Text #9

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.8993. Min Act: -0.0000

Data Index: 1552027 (The Pile)

Max Activating Token Index: 848

Text #10

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.5566. Min Act: -0.0000

Data Index: 1589219 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.3051. Min Act: -0.0000

Data Index: 583159 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.4541. Min Act: -0.0000

Data Index: 484715 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.6716. Min Act: -0.0000

Data Index: 1435486 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.4451. Min Act: -0.0000

Data Index: 886184 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.8004. Min Act: -0.0000

Data Index: 1319280 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.5339. Min Act: -0.0000

Data Index: 376865 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.6524. Min Act: -0.0000

Data Index: 1201686 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.6455. Min Act: -0.0000

Data Index: 916143 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 3.4925. Min Range: -3.4925

Max Act: 2.6402. Min Act: -0.0000

Data Index: 1173152 (The Pile)

Max Activating Token Index: 866