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

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

Neuron 1113 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.8836. Min Act: -0.0000

Data Index: 506959 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7634. Min Act: -0.0000

Data Index: 697541 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7693. Min Act: -0.0000

Data Index: 362459 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7110. Min Act: -0.0000

Data Index: 518521 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7686. Min Act: -0.0000

Data Index: 6671 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1094476 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7174. Min Act: -0.0000

Data Index: 345216 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.7109. Min Act: -0.0000

Data Index: 902711 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6479. Min Act: -0.0000

Data Index: 386640 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1084009 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1052433 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1283368 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6207. Min Act: -0.0000

Data Index: 889627 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1063966 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5946. Min Act: -0.0000

Data Index: 783688 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6239. Min Act: -0.0000

Data Index: 761008 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5613. Min Act: -0.0000

Data Index: 939534 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.6056. Min Act: -0.0000

Data Index: 423674 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5743. Min Act: -0.0000

Data Index: 307993 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.8836. Min Range: -0.8836

Max Act: 0.5753. Min Act: -0.0000

Data Index: 951590 (C4 (Web Text))

Max Activating Token Index: 769