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

Dataset: The Pile

Neuron 2627 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: 5.4464. Min Range: -5.4464

Max Act: 5.4464. Min Act: -0.0001

Data Index: 838333 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.7875. Min Act: -0.0000

Data Index: 1283258 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.7350. Min Act: -0.0000

Data Index: 1015840 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 5.4464. Min Range: -5.4464

Max Act: 5.0760. Min Act: -0.0000

Data Index: 1220789 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 5.4464. Min Range: -5.4464

Max Act: 5.0940. Min Act: -0.0000

Data Index: 1258612 (The Pile)

Max Activating Token Index: 122

Text #5

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.9286. Min Act: -0.0000

Data Index: 1964351 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.7413. Min Act: -0.0000

Data Index: 679845 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.7356. Min Act: -0.0000

Data Index: 778715 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.7002. Min Act: -0.0000

Data Index: 972884 (The Pile)

Max Activating Token Index: 18

Text #9

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.8354. Min Act: -0.0000

Data Index: 1558874 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.6615. Min Act: -0.0000

Data Index: 1501528 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.4667. Min Act: -0.0000

Data Index: 1873872 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.4498. Min Act: -0.0000

Data Index: 539632 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.6021. Min Act: -0.0000

Data Index: 1669390 (The Pile)

Max Activating Token Index: 472

Text #14

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.7604. Min Act: -0.0000

Data Index: 1117502 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.7477. Min Act: -0.0000

Data Index: 1845866 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.4195. Min Act: -0.0000

Data Index: 316851 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.5751. Min Act: -0.0000

Data Index: 990307 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.5105. Min Act: -0.0000

Data Index: 1875413 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 5.4464. Min Range: -5.4464

Max Act: 4.8529. Min Act: -0.0000

Data Index: 1379260 (The Pile)

Max Activating Token Index: 155