Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 467 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1886. Min Range: -1.1886

Max Act: 1.1886. Min Act: -0.0000

Data Index: 749111 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 1.1886. Min Range: -1.1886

Max Act: 1.1511. Min Act: -0.0000

Data Index: 1214068 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.1886. Min Range: -1.1886

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1038966 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 1.1886. Min Range: -1.1886

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1294565 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 1.1886. Min Range: -1.1886

Max Act: 1.0060. Min Act: -0.0001

Data Index: 579267 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9487. Min Act: -0.0001

Data Index: 494969 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9111. Min Act: -0.0000

Data Index: 513853 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9771. Min Act: -0.0000

Data Index: 56610 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9411. Min Act: -0.0001

Data Index: 380293 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9320. Min Act: -0.0001

Data Index: 1391709 (Python Code)

Max Activating Token Index: 821

Text #10

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1293871 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9390. Min Act: -0.0000

Data Index: 741388 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1042490 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9301. Min Act: -0.0000

Data Index: 921049 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.9000. Min Act: -0.0000

Data Index: 945953 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8741. Min Act: -0.0000

Data Index: 392680 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8428. Min Act: -0.0000

Data Index: 672617 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8378. Min Act: -0.0001

Data Index: 1562295 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8244. Min Act: -0.0000

Data Index: 613310 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.1886. Min Range: -1.1886

Max Act: 0.8866. Min Act: -0.0000

Data Index: 706997 (C4 (Web Text))

Max Activating Token Index: 619