Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2144 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0003

Data Index: 580188 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0652. Min Act: -0.0003

Data Index: 323668 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0653. Min Act: -0.0003

Data Index: 418375 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0631. Min Act: -0.0003

Data Index: 517501 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0626. Min Act: -0.0003

Data Index: 354239 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1107597 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0590. Min Act: -0.0003

Data Index: 999361 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1308938 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0546. Min Act: -0.0003

Data Index: 770940 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0583. Min Act: -0.0003

Data Index: 83165 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0526. Min Act: -0.0003

Data Index: 792310 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0547. Min Act: -0.0003

Data Index: 898008 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0542. Min Act: -0.0003

Data Index: 380545 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0515. Min Act: -0.0003

Data Index: 581961 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1312636 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0521. Min Act: -0.0003

Data Index: 304392 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0519. Min Act: -0.0003

Data Index: 780095 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1078640 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1123054 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1281610 (C4 (Web Text))

Max Activating Token Index: 849