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

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

Neuron 2851 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: 2.9982. Min Range: -2.9982

Max Act: 2.9982. Min Act: -0.0000

Data Index: 17070 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.9112. Min Act: -0.0000

Data Index: 768951 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.7398. Min Act: -0.0000

Data Index: 1261678 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.6017. Min Act: -0.0000

Data Index: 1119976 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.5886. Min Act: -0.0000

Data Index: 14312 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.5110. Min Act: -0.0000

Data Index: 663954 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.1149. Min Act: -0.0000

Data Index: 1292758 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.1824. Min Act: -0.0000

Data Index: 866131 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.1161. Min Act: -0.0000

Data Index: 1309615 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.0971. Min Act: -0.0000

Data Index: 626714 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 2.9982. Min Range: -2.9982

Max Act: 1.9778. Min Act: -0.0000

Data Index: 445490 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.1952. Min Act: -0.0000

Data Index: 578782 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 2.9982. Min Range: -2.9982

Max Act: 2.0594. Min Act: -0.0000

Data Index: 109051 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 2.9982. Min Range: -2.9982

Max Act: 1.8878. Min Act: -0.0000

Data Index: 1281685 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 2.9982. Min Range: -2.9982

Max Act: 1.9808. Min Act: -0.0000

Data Index: 766346 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 2.9982. Min Range: -2.9982

Max Act: 1.8571. Min Act: -0.0000

Data Index: 785824 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 2.9982. Min Range: -2.9982

Max Act: 1.9588. Min Act: -0.0000

Data Index: 1149772 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 2.9982. Min Range: -2.9982

Max Act: 1.9586. Min Act: -0.0000

Data Index: 1064386 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 2.9982. Min Range: -2.9982

Max Act: 1.9515. Min Act: -0.0000

Data Index: 220004 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 2.9982. Min Range: -2.9982

Max Act: 1.8502. Min Act: -0.0000

Data Index: 500689 (C4 (Web Text))

Max Activating Token Index: 833