Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2225 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0003

Data Index: 226276 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0791. Min Act: -0.0003

Data Index: 837247 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0694. Min Act: -0.0003

Data Index: 84791 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0719. Min Act: -0.0003

Data Index: 622055 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0615. Min Act: -0.0003

Data Index: 593649 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0705. Min Act: -0.0003

Data Index: 651785 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0673. Min Act: -0.0003

Data Index: 396369 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1096663 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1348946 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0660. Min Act: -0.0003

Data Index: 380639 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0612. Min Act: -0.0003

Data Index: 98502 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0656. Min Act: -0.0003

Data Index: 192480 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0653. Min Act: -0.0003

Data Index: 139560 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0607. Min Act: -0.0003

Data Index: 480281 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0668. Min Act: -0.0003

Data Index: 839408 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1310030 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0597. Min Act: -0.0003

Data Index: 457599 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1090587 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0697. Min Act: -0.0003

Data Index: 397206 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0669. Min Act: -0.0003

Data Index: 718094 (C4 (Web Text))

Max Activating Token Index: 471