Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1611 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0002

Data Index: 278268 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1463964 (Python Code)

Max Activating Token Index: 84

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0716. Min Act: -0.0002

Data Index: 848901 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0715. Min Act: -0.0002

Data Index: 427616 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0715. Min Act: -0.0002

Data Index: 395584 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0709. Min Act: -0.0002

Data Index: 650543 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0685. Min Act: -0.0002

Data Index: 931793 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1275679 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0690. Min Act: -0.0002

Data Index: 534971 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0688. Min Act: -0.0002

Data Index: 458139 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0677. Min Act: -0.0002

Data Index: 705535 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0683. Min Act: -0.0002

Data Index: 299555 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1576327 (Python Code)

Max Activating Token Index: 190

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0682. Min Act: -0.0002

Data Index: 394676 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0694. Min Act: -0.0002

Data Index: 518327 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1463551 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0673. Min Act: -0.0002

Data Index: 423229 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1160212 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1299170 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1166575 (C4 (Web Text))

Max Activating Token Index: 66