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

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

Neuron 5698 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.3532. Min Act: -0.0000

Data Index: 501045 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.1581. Min Act: -0.0000

Data Index: 207830 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.1621. Min Act: -0.0000

Data Index: 678040 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 5.3532. Min Range: -5.3532

Max Act: 4.7992. Min Act: -0.0000

Data Index: 1345894 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 5.3532. Min Range: -5.3532

Max Act: 4.7436. Min Act: -0.0000

Data Index: 763701 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 5.3532. Min Range: -5.3532

Max Act: 5.0787. Min Act: -0.0000

Data Index: 1049521 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 5.3532. Min Range: -5.3532

Max Act: 4.3834. Min Act: -0.0000

Data Index: 129495 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 5.3532. Min Range: -5.3532

Max Act: 4.4423. Min Act: -0.0000

Data Index: 1281827 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 5.3532. Min Range: -5.3532

Max Act: 3.9762. Min Act: -0.0000

Data Index: 1003834 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 5.3532. Min Range: -5.3532

Max Act: 4.0694. Min Act: -0.0000

Data Index: 337337 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 5.3532. Min Range: -5.3532

Max Act: 3.7762. Min Act: -0.0000

Data Index: 746246 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 5.3532. Min Range: -5.3532

Max Act: 3.4954. Min Act: -0.0000

Data Index: 1330686 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 5.3532. Min Range: -5.3532

Max Act: 3.6069. Min Act: -0.0000

Data Index: 922723 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 5.3532. Min Range: -5.3532

Max Act: 3.7246. Min Act: -0.0000

Data Index: 591484 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 5.3532. Min Range: -5.3532

Max Act: 3.2521. Min Act: -0.0000

Data Index: 366059 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 5.3532. Min Range: -5.3532

Max Act: 3.3088. Min Act: -0.0000

Data Index: 15786 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 5.3532. Min Range: -5.3532

Max Act: 3.1003. Min Act: -0.0000

Data Index: 655057 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 5.3532. Min Range: -5.3532

Max Act: 3.0063. Min Act: -0.0000

Data Index: 661377 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 5.3532. Min Range: -5.3532

Max Act: 2.9814. Min Act: -0.0000

Data Index: 1164520 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 5.3532. Min Range: -5.3532

Max Act: 2.8536. Min Act: -0.0000

Data Index: 1067909 (C4 (Web Text))

Max Activating Token Index: 818