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

Dataset: The Pile

Neuron 4207 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: 1.2806. Min Range: -1.2806

Max Act: 1.2806. Min Act: -0.0000

Data Index: 1952686 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 1.2806. Min Range: -1.2806

Max Act: 1.0374. Min Act: -0.0000

Data Index: 922908 (The Pile)

Max Activating Token Index: 550

Text #2

Max Range: 1.2806. Min Range: -1.2806

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1630051 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1334290 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.9571. Min Act: -0.0000

Data Index: 415883 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1576715 (The Pile)

Max Activating Token Index: 721

Text #6

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.9457. Min Act: -0.0000

Data Index: 528615 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1012127 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1711659 (The Pile)

Max Activating Token Index: 700

Text #9

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1954099 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8876. Min Act: -0.0000

Data Index: 573162 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1914488 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8755. Min Act: -0.0000

Data Index: 961551 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8452. Min Act: 0.0000

Data Index: 946292 (The Pile)

Max Activating Token Index: 520

Text #14

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8365. Min Act: -0.0000

Data Index: 406619 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8934. Min Act: -0.0000

Data Index: 920926 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8405. Min Act: -0.0000

Data Index: 1989215 (The Pile)

Max Activating Token Index: 507

Text #17

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8357. Min Act: -0.0000

Data Index: 749599 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1362361 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8155. Min Act: -0.0000

Data Index: 202971 (The Pile)

Max Activating Token Index: 193