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

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

Neuron 942 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1633731 (Python Code)

Max Activating Token Index: 255

Text #1

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1191114 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1350051 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3601. Min Act: -0.0000

Data Index: 920195 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1589911 (Python Code)

Max Activating Token Index: 1007

Text #5

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3335. Min Act: -0.0000

Data Index: 458543 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1575027 (Python Code)

Max Activating Token Index: 847

Text #7

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1520276 (Python Code)

Max Activating Token Index: 456

Text #8

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1393912 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2814. Min Act: -0.0000

Data Index: 788882 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1621148 (Python Code)

Max Activating Token Index: 259

Text #11

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2627. Min Act: -0.0000

Data Index: 256530 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2813. Min Act: -0.0000

Data Index: 881801 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1515345 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1378660 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1519054 (Python Code)

Max Activating Token Index: 287

Text #16

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2514. Min Act: -0.0000

Data Index: 241698 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1582655 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2558. Min Act: -0.0000

Data Index: 334496 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1456449 (Python Code)

Max Activating Token Index: 789