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

Dataset: The Pile

Neuron 3260 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1993707 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4880. Min Act: -0.0000

Data Index: 900840 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4287. Min Act: -0.0000

Data Index: 451702 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4125. Min Act: -0.0000

Data Index: 441017 (The Pile)

Max Activating Token Index: 155

Text #4

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4691. Min Act: -0.0000

Data Index: 570513 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4723. Min Act: -0.0000

Data Index: 706382 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4205. Min Act: -0.0000

Data Index: 460206 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3002. Min Act: -0.0000

Data Index: 292608 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1703397 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1590274 (The Pile)

Max Activating Token Index: 362

Text #10

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3354. Min Act: -0.0000

Data Index: 296390 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1866057 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2178. Min Act: -0.0000

Data Index: 1931992 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1020574 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3429. Min Act: -0.0000

Data Index: 143559 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3100. Min Act: -0.0000

Data Index: 147578 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3063. Min Act: -0.0000

Data Index: 821900 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3443. Min Act: -0.0000

Data Index: 840612 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2609. Min Act: -0.0000

Data Index: 918592 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.2487. Min Act: -0.0000

Data Index: 308429 (The Pile)

Max Activating Token Index: 67