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

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

Neuron 5358 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7582. Min Range: -5.7582

Max Act: 5.7582. Min Act: -0.0000

Data Index: 1199448 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.9427. Min Act: -0.0000

Data Index: 570692 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.8838. Min Act: -0.0000

Data Index: 103307 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.5378. Min Act: -0.0000

Data Index: 293479 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.4784. Min Act: -0.0000

Data Index: 784075 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.2615. Min Act: -0.0000

Data Index: 195774 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.0896. Min Act: -0.0000

Data Index: 1282937 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.3960. Min Act: -0.0000

Data Index: 267442 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.1860. Min Act: -0.0000

Data Index: 1296684 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.1608. Min Act: -0.0000

Data Index: 49818 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.1431. Min Act: -0.0000

Data Index: 902243 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.2546. Min Act: -0.0000

Data Index: 369083 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.0561. Min Act: -0.0000

Data Index: 695660 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.1707. Min Act: -0.0000

Data Index: 90613 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 5.7582. Min Range: -5.7582

Max Act: 3.9733. Min Act: -0.0000

Data Index: 1187492 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 5.7582. Min Range: -5.7582

Max Act: 3.7574. Min Act: -0.0000

Data Index: 476374 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 5.7582. Min Range: -5.7582

Max Act: 3.8379. Min Act: -0.0000

Data Index: 704526 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 5.7582. Min Range: -5.7582

Max Act: 4.0175. Min Act: -0.0000

Data Index: 331151 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 5.7582. Min Range: -5.7582

Max Act: 3.5791. Min Act: -0.0000

Data Index: 642854 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 5.7582. Min Range: -5.7582

Max Act: 3.7471. Min Act: -0.0000

Data Index: 583742 (C4 (Web Text))

Max Activating Token Index: 450