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

Dataset: The Pile

Neuron 4684 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.9751. Min Act: -0.0000

Data Index: 545059 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.8671. Min Act: -0.0000

Data Index: 229492 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.9503. Min Act: -0.0000

Data Index: 828596 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.8364. Min Act: -0.0000

Data Index: 1406415 (The Pile)

Max Activating Token Index: 414

Text #4

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5881. Min Act: -0.0000

Data Index: 216392 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1407845 (The Pile)

Max Activating Token Index: 466

Text #6

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5364. Min Act: -0.0000

Data Index: 710520 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.7165. Min Act: -0.0000

Data Index: 1635724 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4268. Min Act: -0.0000

Data Index: 1453584 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5023. Min Act: -0.0000

Data Index: 469160 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4046. Min Act: -0.0000

Data Index: 351596 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3258. Min Act: -0.0000

Data Index: 1079441 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1569623 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5811. Min Act: -0.0000

Data Index: 77542 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3904. Min Act: -0.0000

Data Index: 1510734 (The Pile)

Max Activating Token Index: 589

Text #15

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1039519 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4565. Min Act: -0.0000

Data Index: 219103 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3532. Min Act: -0.0000

Data Index: 676782 (The Pile)

Max Activating Token Index: 39

Text #18

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4225. Min Act: -0.0000

Data Index: 1836859 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4953. Min Act: -0.0000

Data Index: 1708098 (The Pile)

Max Activating Token Index: 384