Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1936 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.7105. Min Act: -0.0000

Data Index: 1360609 (Python Code)

Max Activating Token Index: 904

Text #1

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.7007. Min Act: -0.0000

Data Index: 1407131 (Python Code)

Max Activating Token Index: 1015

Text #2

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.4685. Min Act: -0.0000

Data Index: 1652147 (Python Code)

Max Activating Token Index: 49

Text #3

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.5437. Min Act: -0.0000

Data Index: 1449275 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.4922. Min Act: -0.0000

Data Index: 1622703 (Python Code)

Max Activating Token Index: 613

Text #5

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.4536. Min Act: -0.0000

Data Index: 1465748 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.3065. Min Act: -0.0000

Data Index: 1638235 (Python Code)

Max Activating Token Index: 247

Text #7

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.2854. Min Act: -0.0000

Data Index: 1398473 (Python Code)

Max Activating Token Index: 793

Text #8

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1479106 (Python Code)

Max Activating Token Index: 852

Text #9

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.4277. Min Act: -0.0000

Data Index: 1432132 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1494514 (Python Code)

Max Activating Token Index: 738

Text #11

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1488972 (Python Code)

Max Activating Token Index: 979

Text #12

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.2450. Min Act: -0.0000

Data Index: 1438098 (Python Code)

Max Activating Token Index: 619

Text #13

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1591515 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.4018. Min Act: -0.0000

Data Index: 1383471 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.1892. Min Act: -0.0000

Data Index: 1597662 (Python Code)

Max Activating Token Index: 873

Text #16

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1480745 (Python Code)

Max Activating Token Index: 852

Text #17

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1493060 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1406720 (Python Code)

Max Activating Token Index: 304

Text #19

Max Range: 1.7105. Min Range: -1.7105

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1432584 (Python Code)

Max Activating Token Index: 288