Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2884 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3825. Min Act: -0.0001

Data Index: 1388626 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3459. Min Act: -0.0001

Data Index: 1622513 (Python Code)

Max Activating Token Index: 124

Text #2

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3483. Min Act: -0.0001

Data Index: 1463396 (Python Code)

Max Activating Token Index: 183

Text #3

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3250. Min Act: -0.0001

Data Index: 1633944 (Python Code)

Max Activating Token Index: 298

Text #4

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3402. Min Act: -0.0001

Data Index: 1586530 (Python Code)

Max Activating Token Index: 283

Text #5

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1425783 (Python Code)

Max Activating Token Index: 403

Text #6

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1478180 (Python Code)

Max Activating Token Index: 478

Text #7

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1570811 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1425333 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3120. Min Act: -0.0001

Data Index: 1396827 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3087. Min Act: -0.0001

Data Index: 1524275 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1575270 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1522585 (Python Code)

Max Activating Token Index: 271

Text #13

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2611. Min Act: -0.0001

Data Index: 1479122 (Python Code)

Max Activating Token Index: 812

Text #14

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3076. Min Act: -0.0001

Data Index: 1399860 (Python Code)

Max Activating Token Index: 356

Text #15

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2774. Min Act: -0.0001

Data Index: 1581822 (Python Code)

Max Activating Token Index: 377

Text #16

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1490748 (Python Code)

Max Activating Token Index: 269

Text #17

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1507132 (Python Code)

Max Activating Token Index: 486

Text #18

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3003. Min Act: -0.0001

Data Index: 1616189 (Python Code)

Max Activating Token Index: 917

Text #19

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1497372 (Python Code)

Max Activating Token Index: 130