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

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

Neuron 734 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5147. Min Range: -5.5147

Max Act: 5.5147. Min Act: -0.0001

Data Index: 302009 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 5.5147. Min Range: -5.5147

Max Act: 5.2382. Min Act: -0.0001

Data Index: 501989 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 5.5147. Min Range: -5.5147

Max Act: 5.5042. Min Act: -0.0001

Data Index: 67317 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.8387. Min Act: -0.0000

Data Index: 1342939 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.4917. Min Act: -0.0000

Data Index: 1126396 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.4587. Min Act: -0.0001

Data Index: 745146 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.0387. Min Act: -0.0001

Data Index: 48212 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.6801. Min Act: -0.0000

Data Index: 592090 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.4706. Min Act: -0.0000

Data Index: 489126 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.4532. Min Act: -0.0000

Data Index: 599358 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.5713. Min Act: -0.0001

Data Index: 1111609 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.3896. Min Act: -0.0001

Data Index: 1250709 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.3766. Min Act: -0.0001

Data Index: 860058 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.0594. Min Act: -0.0000

Data Index: 1025924 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.3632. Min Act: -0.0001

Data Index: 856388 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.4614. Min Act: -0.0001

Data Index: 94194 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.2079. Min Act: -0.0001

Data Index: 954614 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.5088. Min Act: -0.0001

Data Index: 1347761 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 5.5147. Min Range: -5.5147

Max Act: 4.1692. Min Act: -0.0001

Data Index: 687971 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 5.5147. Min Range: -5.5147

Max Act: 3.8276. Min Act: -0.0001

Data Index: 1058648 (C4 (Web Text))

Max Activating Token Index: 310