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

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

Neuron 1801 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: 0.0656. Min Range: -0.0656

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1049568 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1640846 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0549. Min Act: -0.0001

Data Index: 693478 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0562. Min Act: -0.0001

Data Index: 579860 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0557. Min Act: -0.0001

Data Index: 973692 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1056822 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0534. Min Act: -0.0001

Data Index: 928583 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0454. Min Act: -0.0001

Data Index: 72065 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1309148 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0458. Min Act: -0.0001

Data Index: 49725 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0521. Min Act: -0.0001

Data Index: 548205 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1563543 (Python Code)

Max Activating Token Index: 122

Text #12

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1607025 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1542320 (Python Code)

Max Activating Token Index: 187

Text #14

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0430. Min Act: -0.0001

Data Index: 815606 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1406232 (Python Code)

Max Activating Token Index: 938

Text #16

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0452. Min Act: -0.0001

Data Index: 918270 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0423. Min Act: -0.0001

Data Index: 98450 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1644024 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1422331 (Python Code)

Max Activating Token Index: 793