Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 440 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.4629. Min Act: -0.0000

Data Index: 861538 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3959. Min Act: -0.0000

Data Index: 998050 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3886. Min Act: -0.0000

Data Index: 908892 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3648. Min Act: -0.0000

Data Index: 792348 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3519. Min Act: -0.0000

Data Index: 444374 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3497. Min Act: -0.0000

Data Index: 415230 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1076071 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3839. Min Act: -0.0000

Data Index: 611002 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1044446 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3634. Min Act: -0.0000

Data Index: 571800 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3276. Min Act: -0.0000

Data Index: 490951 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3235. Min Act: -0.0000

Data Index: 485456 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3112. Min Act: -0.0000

Data Index: 414615 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.2593. Min Act: -0.0000

Data Index: 848529 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.2959. Min Act: -0.0000

Data Index: 295238 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1189510 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.2776. Min Act: -0.0000

Data Index: 116422 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.2701. Min Act: -0.0000

Data Index: 931447 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1267925 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.2526. Min Act: -0.0000

Data Index: 2695 (C4 (Web Text))

Max Activating Token Index: 365