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

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

Neuron 3037 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1361332 (Python Code)

Max Activating Token Index: 730

Text #1

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1410667 (Python Code)

Max Activating Token Index: 678

Text #2

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1430336 (Python Code)

Max Activating Token Index: 591

Text #3

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1498525 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1420010 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1405225 (Python Code)

Max Activating Token Index: 869

Text #6

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1514149 (Python Code)

Max Activating Token Index: 239

Text #7

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1502112 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1399605 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1471484 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1543966 (Python Code)

Max Activating Token Index: 195

Text #11

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1547083 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1484403 (Python Code)

Max Activating Token Index: 872

Text #13

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1544152 (Python Code)

Max Activating Token Index: 567

Text #14

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1421000 (Python Code)

Max Activating Token Index: 176

Text #15

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1380572 (Python Code)

Max Activating Token Index: 255

Text #16

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1533034 (Python Code)

Max Activating Token Index: 1008

Text #17

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1642773 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1640062 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 0.3581. Min Range: -0.3581

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1517724 (Python Code)

Max Activating Token Index: 323