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

Dataset: The Pile

Neuron 2900 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1694176 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.3344. Min Act: -0.0000

Data Index: 216896 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.4131. Min Act: -0.0000

Data Index: 1647354 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1568258 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.3172. Min Act: -0.0000

Data Index: 859386 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.2326. Min Act: -0.0000

Data Index: 1120230 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.2160. Min Act: -0.0000

Data Index: 359858 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1013242 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.1350. Min Act: -0.0000

Data Index: 1481660 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1404184 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.1175. Min Act: -0.0000

Data Index: 1894841 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.0879. Min Act: -0.0000

Data Index: 858694 (The Pile)

Max Activating Token Index: 608

Text #12

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.0767. Min Act: -0.0000

Data Index: 883775 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 1.4474. Min Range: -1.4474

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1343737 (The Pile)

Max Activating Token Index: 893

Text #14

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1865689 (The Pile)

Max Activating Token Index: 250

Text #15

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1341061 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 1.4474. Min Range: -1.4474

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1095865 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.0881. Min Act: -0.0000

Data Index: 665171 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 1.4474. Min Range: -1.4474

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1874700 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 1.4474. Min Range: -1.4474

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1720240 (The Pile)

Max Activating Token Index: 564