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

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

Neuron 964 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.6549. Min Act: -0.0000

Data Index: 144602 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1186969 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.6027. Min Act: -0.0000

Data Index: 989431 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5719. Min Act: -0.0000

Data Index: 827164 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5716. Min Act: -0.0000

Data Index: 991518 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5436. Min Act: -0.0000

Data Index: 433582 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5316. Min Act: -0.0000

Data Index: 871601 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5393. Min Act: -0.0000

Data Index: 713671 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5752. Min Act: -0.0000

Data Index: 383617 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5048. Min Act: -0.0000

Data Index: 814591 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4920. Min Act: -0.0000

Data Index: 681684 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1092455 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1442908 (Python Code)

Max Activating Token Index: 181

Text #13

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.5122. Min Act: -0.0000

Data Index: 650368 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4422. Min Act: -0.0000

Data Index: 666736 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4588. Min Act: -0.0000

Data Index: 335434 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4197. Min Act: -0.0000

Data Index: 243807 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1165486 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4668. Min Act: -0.0000

Data Index: 21091 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.6549. Min Range: -0.6549

Max Act: 0.4061. Min Act: -0.0000

Data Index: 100974 (C4 (Web Text))

Max Activating Token Index: 910