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

Dataset: The Pile

Neuron 2434 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.9881. Min Act: -0.0000

Data Index: 821535 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1346772 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7165. Min Act: -0.0000

Data Index: 316144 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1978100 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1388198 (The Pile)

Max Activating Token Index: 588

Text #5

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1390720 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6746. Min Act: -0.0000

Data Index: 619984 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1873960 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6360. Min Act: -0.0000

Data Index: 458181 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1548790 (The Pile)

Max Activating Token Index: 921

Text #10

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1115011 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1432020 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.5802. Min Act: -0.0000

Data Index: 559426 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6300. Min Act: -0.0000

Data Index: 689391 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6512. Min Act: 0.0000

Data Index: 828662 (The Pile)

Max Activating Token Index: 395

Text #15

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1709661 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.5907. Min Act: -0.0000

Data Index: 881006 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1431851 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1350110 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 0.9881. Min Range: -0.9881

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1339779 (The Pile)

Max Activating Token Index: 100