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

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

Neuron 1300 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1459320 (Python Code)

Max Activating Token Index: 536

Text #1

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1557156 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1394171 (Python Code)

Max Activating Token Index: 824

Text #3

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1495027 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1190231 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1519248 (Python Code)

Max Activating Token Index: 751

Text #6

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1583570 (Python Code)

Max Activating Token Index: 456

Text #7

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1576365 (Python Code)

Max Activating Token Index: 815

Text #8

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0520. Min Act: -0.0000

Data Index: 73580 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0560. Min Act: -0.0000

Data Index: 235023 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1619788 (Python Code)

Max Activating Token Index: 605

Text #11

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1042799 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0538. Min Act: -0.0000

Data Index: 563310 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0513. Min Act: -0.0000

Data Index: 542140 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1471480 (Python Code)

Max Activating Token Index: 124

Text #15

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1575841 (Python Code)

Max Activating Token Index: 1014

Text #16

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1561203 (Python Code)

Max Activating Token Index: 931

Text #17

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1445266 (Python Code)

Max Activating Token Index: 340

Text #18

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1465857 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0507. Min Act: -0.0000

Data Index: 926518 (C4 (Web Text))

Max Activating Token Index: 107