Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 429 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1110663 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0617. Min Act: -0.0002

Data Index: 262718 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1088970 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0641. Min Act: -0.0002

Data Index: 445588 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0616. Min Act: -0.0002

Data Index: 371064 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0571. Min Act: -0.0002

Data Index: 675522 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0572. Min Act: 0.0001

Data Index: 1624144 (Python Code)

Max Activating Token Index: 948

Text #7

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1211470 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0559. Min Act: 0.0001

Data Index: 1591214 (Python Code)

Max Activating Token Index: 514

Text #9

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0541. Min Act: -0.0002

Data Index: 800840 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1364508 (Python Code)

Max Activating Token Index: 616

Text #11

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0539. Min Act: -0.0001

Data Index: 126198 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1171963 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0529. Min Act: 0.0001

Data Index: 503618 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0536. Min Act: -0.0001

Data Index: 631291 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1088836 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0518. Min Act: -0.0002

Data Index: 980740 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0524. Min Act: -0.0002

Data Index: 563914 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1639860 (Python Code)

Max Activating Token Index: 934

Text #19

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1213113 (C4 (Web Text))

Max Activating Token Index: 237