Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3961 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.6675. Min Act: -0.0001

Data Index: 774438 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5465. Min Act: -0.0002

Data Index: 167655 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5746. Min Act: -0.0002

Data Index: 289698 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4875. Min Act: -0.0002

Data Index: 491549 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5527. Min Act: -0.0002

Data Index: 388623 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5251. Min Act: -0.0002

Data Index: 1325504 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4894. Min Act: -0.0002

Data Index: 36120 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4994. Min Act: -0.0002

Data Index: 292052 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4805. Min Act: -0.0002

Data Index: 17516 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4889. Min Act: -0.0002

Data Index: 640637 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4893. Min Act: -0.0001

Data Index: 1167465 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4716. Min Act: -0.0002

Data Index: 620457 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5157. Min Act: -0.0001

Data Index: 380781 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.5011. Min Act: -0.0001

Data Index: 154527 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4757. Min Act: -0.0002

Data Index: 583219 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4707. Min Act: -0.0001

Data Index: 57601 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4944. Min Act: -0.0002

Data Index: 270572 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4684. Min Act: -0.0002

Data Index: 205221 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4283. Min Act: -0.0002

Data Index: 1294439 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.6675. Min Range: -0.6675

Max Act: 0.4484. Min Act: -0.0002

Data Index: 321987 (C4 (Web Text))

Max Activating Token Index: 897