Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2079 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.8579. Min Act: -0.0000

Data Index: 910564 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.9588. Min Act: -0.0000

Data Index: 828110 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.7157. Min Act: -0.0000

Data Index: 1148700 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.3254. Min Act: -0.0000

Data Index: 1321819 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.4416. Min Act: -0.0000

Data Index: 65995 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.2612. Min Act: -0.0000

Data Index: 1547707 (Python Code)

Max Activating Token Index: 954

Text #6

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.2453. Min Act: -0.0000

Data Index: 978619 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.3531. Min Act: -0.0000

Data Index: 154847 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.1651. Min Act: -0.0000

Data Index: 600886 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 3.9588. Min Range: -3.9588

Max Act: 2.9745. Min Act: -0.0000

Data Index: 679459 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.0724. Min Act: -0.0000

Data Index: 1535281 (Python Code)

Max Activating Token Index: 683

Text #11

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.0379. Min Act: -0.0000

Data Index: 208999 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 3.9588. Min Range: -3.9588

Max Act: 2.9671. Min Act: -0.0000

Data Index: 673319 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 3.9588. Min Range: -3.9588

Max Act: 2.9719. Min Act: -0.0000

Data Index: 924898 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 3.9588. Min Range: -3.9588

Max Act: 2.9275. Min Act: -0.0000

Data Index: 967080 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 3.9588. Min Range: -3.9588

Max Act: 2.9223. Min Act: -0.0000

Data Index: 818642 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 3.9588. Min Range: -3.9588

Max Act: 2.9109. Min Act: -0.0000

Data Index: 403638 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 3.9588. Min Range: -3.9588

Max Act: 2.8906. Min Act: -0.0000

Data Index: 487958 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 3.9588. Min Range: -3.9588

Max Act: 2.8783. Min Act: -0.0000

Data Index: 333866 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 3.9588. Min Range: -3.9588

Max Act: 2.8591. Min Act: -0.0000

Data Index: 114870 (C4 (Web Text))

Max Activating Token Index: 2