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

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

Neuron 2584 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.7011. Min Act: -0.0000

Data Index: 612632 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4922. Min Act: -0.0000

Data Index: 203382 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4642. Min Act: -0.0000

Data Index: 484392 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1487531 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1468595 (Python Code)

Max Activating Token Index: 378

Text #5

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1554787 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4412. Min Act: -0.0000

Data Index: 856588 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4392. Min Act: -0.0000

Data Index: 380060 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1403806 (Python Code)

Max Activating Token Index: 842

Text #9

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1036240 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1445417 (Python Code)

Max Activating Token Index: 946

Text #11

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4076. Min Act: -0.0000

Data Index: 568599 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1370847 (Python Code)

Max Activating Token Index: 336

Text #13

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.3966. Min Act: -0.0000

Data Index: 425474 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.3955. Min Act: 0.0000

Data Index: 1531421 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1376938 (Python Code)

Max Activating Token Index: 790

Text #16

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1430676 (Python Code)

Max Activating Token Index: 20

Text #17

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.3891. Min Act: 0.0000

Data Index: 1504528 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.3788. Min Act: -0.0000

Data Index: 699480 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.7011. Min Range: -0.7011

Max Act: 0.3713. Min Act: -0.0000

Data Index: 452889 (C4 (Web Text))

Max Activating Token Index: 245