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

Dataset: The Pile

Neuron 3860 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: 0.7929. Min Range: -0.7929

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1285238 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.7929. Min Act: -0.0000

Data Index: 255710 (The Pile)

Max Activating Token Index: 507

Text #2

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.7212. Min Act: -0.0000

Data Index: 15292 (The Pile)

Max Activating Token Index: 429

Text #3

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1050743 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1224599 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1866521 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1463187 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.7235. Min Act: -0.0000

Data Index: 905957 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6666. Min Act: -0.0000

Data Index: 726528 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6848. Min Act: -0.0000

Data Index: 488008 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1571692 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6583. Min Act: -0.0000

Data Index: 41133 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1701333 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1449115 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6193. Min Act: -0.0000

Data Index: 356354 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1280852 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1316809 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6186. Min Act: -0.0000

Data Index: 390987 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1206012 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 0.7929. Min Range: -0.7929

Max Act: 0.6269. Min Act: -0.0000

Data Index: 755450 (The Pile)

Max Activating Token Index: 65