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

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

Neuron 1634 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.3962. Min Act: -0.0000

Data Index: 1085173 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.3908. Min Act: 0.0000

Data Index: 395815 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.3387. Min Act: -0.0000

Data Index: 119175 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.3084. Min Act: -0.0000

Data Index: 1242628 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.1425. Min Act: -0.0000

Data Index: 1019090 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.0338. Min Act: -0.0000

Data Index: 119110 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.1343. Min Act: -0.0000

Data Index: 197999 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.1266. Min Act: -0.0000

Data Index: 296354 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 2.3962. Min Range: -2.3962

Max Act: 1.9941. Min Act: -0.0000

Data Index: 511639 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 2.3962. Min Range: -2.3962

Max Act: 1.9333. Min Act: -0.0000

Data Index: 73419 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.0318. Min Act: -0.0000

Data Index: 1326723 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 2.3962. Min Range: -2.3962

Max Act: 1.9198. Min Act: -0.0000

Data Index: 416732 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.1391. Min Act: -0.0000

Data Index: 550657 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 2.3962. Min Range: -2.3962

Max Act: 1.9843. Min Act: -0.0000

Data Index: 1030122 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 2.3962. Min Range: -2.3962

Max Act: 1.9627. Min Act: -0.0000

Data Index: 201969 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 2.3962. Min Range: -2.3962

Max Act: 1.8468. Min Act: -0.0000

Data Index: 647508 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 2.3962. Min Range: -2.3962

Max Act: 1.8506. Min Act: -0.0000

Data Index: 678271 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 2.3962. Min Range: -2.3962

Max Act: 2.0389. Min Act: -0.0000

Data Index: 935687 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 2.3962. Min Range: -2.3962

Max Act: 1.8686. Min Act: -0.0000

Data Index: 489051 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 2.3962. Min Range: -2.3962

Max Act: 1.9965. Min Act: -0.0000

Data Index: 76044 (C4 (Web Text))

Max Activating Token Index: 857