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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3047 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1055. Min Range: -2.1055

Max Act: 2.1055. Min Act: -0.0000

Data Index: 1358202 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 2.1055. Min Range: -2.1055

Max Act: 2.0218. Min Act: -0.0000

Data Index: 667105 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 2.1055. Min Range: -2.1055

Max Act: 2.0034. Min Act: -0.0000

Data Index: 159218 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 2.1055. Min Range: -2.1055

Max Act: 2.0848. Min Act: -0.0000

Data Index: 541664 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.9155. Min Act: -0.0000

Data Index: 275255 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.9144. Min Act: -0.0001

Data Index: 257999 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.9692. Min Act: -0.0000

Data Index: 806620 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.8718. Min Act: -0.0000

Data Index: 558221 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.8776. Min Act: -0.0001

Data Index: 860473 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.8901. Min Act: -0.0000

Data Index: 1003489 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.7770. Min Act: -0.0000

Data Index: 1035543 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.6850. Min Act: -0.0000

Data Index: 331707 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1161046 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.6451. Min Act: -0.0000

Data Index: 327361 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.6542. Min Act: -0.0000

Data Index: 1174215 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.5764. Min Act: -0.0000

Data Index: 386653 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.5268. Min Act: -0.0000

Data Index: 811400 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.5703. Min Act: -0.0001

Data Index: 306588 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.5897. Min Act: -0.0001

Data Index: 212392 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 2.1055. Min Range: -2.1055

Max Act: 1.5294. Min Act: -0.0000

Data Index: 311377 (C4 (Web Text))

Max Activating Token Index: 55