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

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

Neuron 544 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: 0.9509. Min Range: -0.9509

Max Act: 0.9509. Min Act: -0.0000

Data Index: 252504 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.9344. Min Act: -0.0000

Data Index: 947399 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8566. Min Act: -0.0000

Data Index: 440113 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8561. Min Act: -0.0000

Data Index: 159064 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8502. Min Act: -0.0000

Data Index: 828906 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8179. Min Act: -0.0000

Data Index: 398772 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1003924 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8236. Min Act: -0.0000

Data Index: 623325 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7902. Min Act: -0.0000

Data Index: 675037 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8073. Min Act: -0.0000

Data Index: 134258 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1359213 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7691. Min Act: -0.0000

Data Index: 554705 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7704. Min Act: -0.0000

Data Index: 926092 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1332210 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7772. Min Act: -0.0000

Data Index: 688458 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1300495 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7588. Min Act: -0.0000

Data Index: 442813 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1220925 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7790. Min Act: -0.0000

Data Index: 924759 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7572. Min Act: -0.0000

Data Index: 389725 (C4 (Web Text))

Max Activating Token Index: 336