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

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

Neuron 5382 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: 2.1592. Min Range: -2.1592

Max Act: 2.0812. Min Act: -0.0000

Data Index: 361055 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 2.1592. Min Range: -2.1592

Max Act: 2.1592. Min Act: -0.0000

Data Index: 173453 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.9095. Min Act: -0.0000

Data Index: 468951 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.9892. Min Act: -0.0000

Data Index: 427888 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.7367. Min Act: 0.0000

Data Index: 746487 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.6178. Min Act: -0.0000

Data Index: 37520 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.6544. Min Act: -0.0000

Data Index: 742172 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.6661. Min Act: -0.0000

Data Index: 141118 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.6370. Min Act: -0.0000

Data Index: 762922 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1260699 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.6131. Min Act: -0.0000

Data Index: 902160 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.5970. Min Act: -0.0000

Data Index: 611445 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.5952. Min Act: -0.0000

Data Index: 264938 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.5684. Min Act: -0.0000

Data Index: 687482 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.5505. Min Act: 0.0001

Data Index: 74523 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.6564. Min Act: -0.0000

Data Index: 433073 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.5497. Min Act: -0.0000

Data Index: 1136748 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.5303. Min Act: -0.0000

Data Index: 178148 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.4486. Min Act: -0.0000

Data Index: 658611 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 2.1592. Min Range: -2.1592

Max Act: 1.6087. Min Act: 0.0000

Data Index: 847823 (C4 (Web Text))

Max Activating Token Index: 332