Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2928 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1484416 (Python Code)

Max Activating Token Index: 935

Text #1

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1490770 (Python Code)

Max Activating Token Index: 619

Text #2

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1061782 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0606. Min Act: -0.0001

Data Index: 18066 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1534717 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1341761 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1112505 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0609. Min Act: -0.0001

Data Index: 936494 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0558. Min Act: -0.0001

Data Index: 338579 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1086662 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0517. Min Act: -0.0001

Data Index: 608743 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1474054 (Python Code)

Max Activating Token Index: 818

Text #12

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1466054 (Python Code)

Max Activating Token Index: 394

Text #13

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1369076 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1119888 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1610029 (Python Code)

Max Activating Token Index: 655

Text #16

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0472. Min Act: -0.0001

Data Index: 394935 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1456690 (Python Code)

Max Activating Token Index: 672

Text #18

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0492. Min Act: -0.0001

Data Index: 563173 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1474683 (Python Code)

Max Activating Token Index: 647