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

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

Neuron 4094 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3770. Min Act: -0.0000

Data Index: 545505 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3442. Min Act: -0.0000

Data Index: 820713 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3491. Min Act: -0.0000

Data Index: 358908 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3285. Min Act: -0.0000

Data Index: 397575 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3389. Min Act: -0.0000

Data Index: 505625 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1333514 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3311. Min Act: -0.0000

Data Index: 869776 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1280112 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3148. Min Act: -0.0000

Data Index: 348385 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2728. Min Act: -0.0000

Data Index: 613884 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2905. Min Act: -0.0000

Data Index: 943692 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1117811 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1093088 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2808. Min Act: -0.0000

Data Index: 564768 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2913. Min Act: -0.0000

Data Index: 30805 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2408. Min Act: -0.0000

Data Index: 74573 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2874. Min Act: -0.0000

Data Index: 610660 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2700. Min Act: -0.0000

Data Index: 372231 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2759. Min Act: -0.0000

Data Index: 153586 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1054016 (C4 (Web Text))

Max Activating Token Index: 774