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

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

Neuron 358 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.2116. Min Act: -0.0000

Data Index: 799640 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.2948. Min Act: -0.0000

Data Index: 157391 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.3893. Min Act: -0.0000

Data Index: 1190395 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.3969. Min Act: -0.0000

Data Index: 1236577 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.2772. Min Act: -0.0000

Data Index: 1146160 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.3834. Min Act: -0.0000

Data Index: 278217 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.3911. Min Act: -0.0000

Data Index: 1169042 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.2532. Min Act: -0.0000

Data Index: 549549 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.1514. Min Act: -0.0000

Data Index: 798614 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.4731. Min Act: -0.0000

Data Index: 964023 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.2555. Min Act: -0.0000

Data Index: 614105 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.0141. Min Act: -0.0000

Data Index: 514574 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.3124. Min Act: -0.0000

Data Index: 704584 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.3045. Min Act: -0.0000

Data Index: 436794 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.1785. Min Act: -0.0000

Data Index: 435618 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.1632. Min Act: -0.0000

Data Index: 6168 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.1691. Min Act: -0.0000

Data Index: 828831 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.0520. Min Act: -0.0000

Data Index: 768772 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.1537. Min Act: -0.0000

Data Index: 923496 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 2.4731. Min Range: -2.4731

Max Act: 2.0001. Min Act: -0.0000

Data Index: 1233940 (C4 (Web Text))

Max Activating Token Index: 768