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

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

Neuron 2679 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1670. Min Range: -2.1670

Max Act: 2.0782. Min Act: -0.0000

Data Index: 382259 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 2.1670. Min Range: -2.1670

Max Act: 2.1670. Min Act: -0.0000

Data Index: 399678 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 2.1670. Min Range: -2.1670

Max Act: 2.0454. Min Act: -0.0000

Data Index: 1303471 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 2.1670. Min Range: -2.1670

Max Act: 2.0299. Min Act: -0.0000

Data Index: 878986 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.9801. Min Act: -0.0000

Data Index: 523511 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 2.1670. Min Range: -2.1670

Max Act: 2.0573. Min Act: -0.0000

Data Index: 350012 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.9427. Min Act: -0.0000

Data Index: 1093723 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 2.1670. Min Range: -2.1670

Max Act: 2.0430. Min Act: -0.0000

Data Index: 476333 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 2.1670. Min Range: -2.1670

Max Act: 2.0075. Min Act: -0.0000

Data Index: 868426 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.8462. Min Act: -0.0000

Data Index: 707076 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.8338. Min Act: -0.0000

Data Index: 1333478 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.8344. Min Act: -0.0000

Data Index: 384618 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.6666. Min Act: -0.0000

Data Index: 1343377 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.7565. Min Act: -0.0000

Data Index: 1046980 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.7539. Min Act: -0.0000

Data Index: 18942 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.6071. Min Act: -0.0000

Data Index: 647114 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.6903. Min Act: -0.0000

Data Index: 954220 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.6987. Min Act: -0.0000

Data Index: 385919 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.6748. Min Act: -0.0000

Data Index: 549011 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 2.1670. Min Range: -2.1670

Max Act: 1.6757. Min Act: -0.0000

Data Index: 217055 (C4 (Web Text))

Max Activating Token Index: 13