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

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

Neuron 590 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7681. Min Range: -2.7681

Max Act: 2.7681. Min Act: -0.0000

Data Index: 624379 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 2.7681. Min Range: -2.7681

Max Act: 2.5313. Min Act: -0.0000

Data Index: 1030496 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 2.7681. Min Range: -2.7681

Max Act: 2.3762. Min Act: -0.0000

Data Index: 1195660 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 2.7681. Min Range: -2.7681

Max Act: 2.0039. Min Act: -0.0000

Data Index: 221374 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.6774. Min Act: -0.0000

Data Index: 66523 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.7614. Min Act: -0.0000

Data Index: 615099 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.6371. Min Act: -0.0000

Data Index: 913196 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.7922. Min Act: -0.0000

Data Index: 270790 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.7788. Min Act: -0.0000

Data Index: 86414 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.8356. Min Act: -0.0000

Data Index: 275366 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.6917. Min Act: -0.0000

Data Index: 486209 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.4447. Min Act: -0.0000

Data Index: 496141 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.5936. Min Act: -0.0000

Data Index: 296226 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.5465. Min Act: -0.0000

Data Index: 756548 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.3780. Min Act: -0.0000

Data Index: 1303000 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.5904. Min Act: -0.0000

Data Index: 348838 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.4732. Min Act: -0.0000

Data Index: 284815 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.6341. Min Act: -0.0000

Data Index: 1105291 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.3972. Min Act: -0.0000

Data Index: 974829 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 2.7681. Min Range: -2.7681

Max Act: 1.3608. Min Act: -0.0000

Data Index: 776723 (C4 (Web Text))

Max Activating Token Index: 802