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

Dataset: The Pile

Neuron 1021 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: 1.8631. Min Range: -1.8631

Max Act: 1.8208. Min Act: -0.0000

Data Index: 744606 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.8631. Min Act: -0.0000

Data Index: 664357 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.5494. Min Act: -0.0000

Data Index: 1030498 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.5248. Min Act: -0.0000

Data Index: 567118 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.4624. Min Act: -0.0000

Data Index: 1120110 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.4680. Min Act: -0.0000

Data Index: 823589 (The Pile)

Max Activating Token Index: 75

Text #6

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3678. Min Act: -0.0000

Data Index: 929474 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2980. Min Act: -0.0000

Data Index: 937999 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3804. Min Act: -0.0000

Data Index: 1432602 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3462. Min Act: -0.0000

Data Index: 1480551 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3638. Min Act: -0.0000

Data Index: 1116056 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3355. Min Act: -0.0000

Data Index: 1755111 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2802. Min Act: -0.0000

Data Index: 1827083 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3684. Min Act: -0.0000

Data Index: 1192717 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1281365 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1427473 (The Pile)

Max Activating Token Index: 785

Text #16

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3106. Min Act: -0.0000

Data Index: 1364346 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2690. Min Act: -0.0000

Data Index: 586945 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1864365 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1981605 (The Pile)

Max Activating Token Index: 573