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

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

Neuron 2141 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: 0.4768. Min Range: -0.4768

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1594857 (Python Code)

Max Activating Token Index: 238

Text #1

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1564492 (Python Code)

Max Activating Token Index: 211

Text #2

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1382146 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1526532 (Python Code)

Max Activating Token Index: 574

Text #4

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1376775 (Python Code)

Max Activating Token Index: 924

Text #5

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1618676 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1635706 (Python Code)

Max Activating Token Index: 520

Text #7

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1628593 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1629440 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1375762 (Python Code)

Max Activating Token Index: 214

Text #10

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1574651 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1629364 (Python Code)

Max Activating Token Index: 625

Text #12

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1426673 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1585358 (Python Code)

Max Activating Token Index: 497

Text #14

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1449335 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1637381 (Python Code)

Max Activating Token Index: 718

Text #16

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1474173 (Python Code)

Max Activating Token Index: 811

Text #17

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1417914 (Python Code)

Max Activating Token Index: 985

Text #18

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1533898 (Python Code)

Max Activating Token Index: 532

Text #19

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1485682 (Python Code)

Max Activating Token Index: 103