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

Dataset: The Pile

Neuron 550 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: 0.6431. Min Range: -0.6431

Max Act: 0.6431. Min Act: -0.0000

Data Index: 596641 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1006906 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.4730. Min Act: -0.0000

Data Index: 529367 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3865. Min Act: -0.0000

Data Index: 428344 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3862. Min Act: -0.0000

Data Index: 237117 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3793. Min Act: -0.0000

Data Index: 411703 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3755. Min Act: -0.0000

Data Index: 827615 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1618511 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1828384 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1312368 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3416. Min Act: -0.0000

Data Index: 15847 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1675184 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1304053 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3086. Min Act: -0.0000

Data Index: 545559 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1499905 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1685104 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3374. Min Act: -0.0000

Data Index: 235890 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1806413 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.3038. Min Act: -0.0000

Data Index: 358518 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 0.6431. Min Range: -0.6431

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1244944 (The Pile)

Max Activating Token Index: 760