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

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

Neuron 2883 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: 2.0712. Min Range: -2.0712

Max Act: 2.0712. Min Act: -0.0000

Data Index: 448817 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.7058. Min Act: -0.0000

Data Index: 205248 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1585204 (Python Code)

Max Activating Token Index: 607

Text #3

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.4349. Min Act: -0.0000

Data Index: 971702 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1490641 (Python Code)

Max Activating Token Index: 707

Text #5

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.2853. Min Act: -0.0000

Data Index: 457083 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.2838. Min Act: -0.0000

Data Index: 677949 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1085369 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.2109. Min Act: -0.0000

Data Index: 858852 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.2110. Min Act: -0.0000

Data Index: 335986 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.1347. Min Act: -0.0000

Data Index: 1271732 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.1265. Min Act: -0.0000

Data Index: 241629 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1580293 (Python Code)

Max Activating Token Index: 438

Text #13

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.1159. Min Act: -0.0000

Data Index: 400744 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1608369 (Python Code)

Max Activating Token Index: 798

Text #15

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.0757. Min Act: -0.0000

Data Index: 729793 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 2.0712. Min Range: -2.0712

Max Act: 0.9419. Min Act: -0.0000

Data Index: 471984 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 2.0712. Min Range: -2.0712

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1313279 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 2.0712. Min Range: -2.0712

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1437672 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 2.0712. Min Range: -2.0712

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1514381 (Python Code)

Max Activating Token Index: 916