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

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

Neuron 4603 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2740. Min Act: -0.0000

Data Index: 122342 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2256. Min Act: -0.0000

Data Index: 543397 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1044565 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1929. Min Act: -0.0001

Data Index: 289960 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1857. Min Act: -0.0000

Data Index: 505187 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1647. Min Act: -0.0001

Data Index: 397150 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2066. Min Act: -0.0000

Data Index: 229336 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1154226 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1707. Min Act: -0.0000

Data Index: 957765 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1184203 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1247299 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1034721 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1054307 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1735. Min Act: -0.0000

Data Index: 161012 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1650. Min Act: -0.0000

Data Index: 464301 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1698. Min Act: -0.0000

Data Index: 222467 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1737. Min Act: -0.0001

Data Index: 237630 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1621. Min Act: -0.0001

Data Index: 530864 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1671. Min Act: -0.0001

Data Index: 982949 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1039883 (C4 (Web Text))

Max Activating Token Index: 776