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

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

Neuron 4979 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2649. Min Range: -2.2649

Max Act: 2.2649. Min Act: -0.0000

Data Index: 857865 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.7531. Min Act: -0.0000

Data Index: 991611 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.6994. Min Act: -0.0000

Data Index: 1040610 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.6039. Min Act: -0.0000

Data Index: 961865 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.6135. Min Act: -0.0000

Data Index: 624856 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1040905 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.2077. Min Act: -0.0000

Data Index: 733231 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.1991. Min Act: -0.0000

Data Index: 148930 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.1893. Min Act: -0.0000

Data Index: 536339 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.2031. Min Act: -0.0000

Data Index: 881685 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.1682. Min Act: -0.0000

Data Index: 49336 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.0885. Min Act: -0.0000

Data Index: 124831 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1112084 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1105119 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 2.2649. Min Range: -2.2649

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1573534 (Python Code)

Max Activating Token Index: 800

Text #15

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.1338. Min Act: -0.0000

Data Index: 1057119 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1206627 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.0974. Min Act: -0.0000

Data Index: 41247 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1232837 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 2.2649. Min Range: -2.2649

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1621648 (Python Code)

Max Activating Token Index: 374