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

Dataset: The Pile

Neuron 1982 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1699046 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3548. Min Act: -0.0000

Data Index: 630789 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.4091. Min Act: -0.0000

Data Index: 1376364 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2855. Min Act: -0.0000

Data Index: 839002 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3044. Min Act: -0.0000

Data Index: 11833 (The Pile)

Max Activating Token Index: 878

Text #5

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1429062 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1222942 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3238. Min Act: -0.0000

Data Index: 1166292 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.3822. Min Act: -0.0000

Data Index: 984397 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2776. Min Act: -0.0000

Data Index: 718698 (The Pile)

Max Activating Token Index: 920

Text #10

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1691633 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.1734. Min Act: -0.0000

Data Index: 293497 (The Pile)

Max Activating Token Index: 261

Text #12

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.0679. Min Act: -0.0000

Data Index: 942813 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.0868. Min Act: -0.0000

Data Index: 103009 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.0654. Min Act: -0.0000

Data Index: 800511 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1772914 (The Pile)

Max Activating Token Index: 701

Text #16

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.0629. Min Act: -0.0000

Data Index: 393960 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1972075 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 1.5631. Min Range: -1.5631

Max Act: 0.9889. Min Act: -0.0000

Data Index: 167267 (The Pile)

Max Activating Token Index: 646

Text #19

Max Range: 1.5631. Min Range: -1.5631

Max Act: 1.0090. Min Act: 0.0000

Data Index: 45999 (The Pile)

Max Activating Token Index: 828