Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2612 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1458. Min Range: -1.1458

Max Act: 1.1458. Min Act: 0.0000

Data Index: 959647 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9900. Min Act: -0.0000

Data Index: 977955 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9068. Min Act: -0.0000

Data Index: 695740 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.9055. Min Act: 0.0002

Data Index: 253937 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8598. Min Act: -0.0000

Data Index: 209208 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.7725. Min Act: 0.0000

Data Index: 622638 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8603. Min Act: -0.0000

Data Index: 455606 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8571. Min Act: 0.0001

Data Index: 749931 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1032319 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1227495 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8417. Min Act: -0.0000

Data Index: 946660 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1120315 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8580. Min Act: -0.0000

Data Index: 772932 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.8078. Min Act: 0.0000

Data Index: 858598 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.7760. Min Act: -0.0000

Data Index: 459041 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.7707. Min Act: 0.0000

Data Index: 727106 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.7595. Min Act: -0.0000

Data Index: 847203 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.7243. Min Act: -0.0000

Data Index: 201636 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.7257. Min Act: 0.0001

Data Index: 1270151 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.1458. Min Range: -1.1458

Max Act: 0.7242. Min Act: -0.0000

Data Index: 332620 (C4 (Web Text))

Max Activating Token Index: 249