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

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

Neuron 1013 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4706. Min Act: -0.0001

Data Index: 504456 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4555. Min Act: -0.0001

Data Index: 266934 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3856. Min Act: -0.0001

Data Index: 503381 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3862. Min Act: -0.0001

Data Index: 739744 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3845. Min Act: -0.0000

Data Index: 738784 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3796. Min Act: -0.0001

Data Index: 1328309 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3833. Min Act: -0.0001

Data Index: 770157 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3806. Min Act: -0.0001

Data Index: 576579 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3800. Min Act: -0.0000

Data Index: 468003 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3791. Min Act: -0.0001

Data Index: 937404 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1040252 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3628. Min Act: -0.0000

Data Index: 668744 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3532. Min Act: -0.0000

Data Index: 268699 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3345. Min Act: -0.0000

Data Index: 920553 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3651. Min Act: -0.0000

Data Index: 331794 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3536. Min Act: -0.0001

Data Index: 873936 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3589. Min Act: -0.0001

Data Index: 1325830 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3401. Min Act: -0.0001

Data Index: 15201 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1015066 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3263. Min Act: -0.0001

Data Index: 1324418 (C4 (Web Text))

Max Activating Token Index: 594