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

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

Neuron 1418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1632371 (Python Code)

Max Activating Token Index: 983

Text #1

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7324. Min Act: -0.0001

Data Index: 1426941 (Python Code)

Max Activating Token Index: 849

Text #2

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1430569 (Python Code)

Max Activating Token Index: 716

Text #3

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1610483 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1650998 (Python Code)

Max Activating Token Index: 910

Text #5

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1470801 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1483712 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1429584 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1466945 (Python Code)

Max Activating Token Index: 909

Text #9

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1395133 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1611840 (Python Code)

Max Activating Token Index: 891

Text #11

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1424540 (Python Code)

Max Activating Token Index: 758

Text #12

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1462587 (Python Code)

Max Activating Token Index: 576

Text #13

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6447. Min Act: -0.0001

Data Index: 1581323 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1459994 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1643623 (Python Code)

Max Activating Token Index: 858

Text #16

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1430298 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1529956 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1573044 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1562360 (Python Code)

Max Activating Token Index: 355