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

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

Neuron 1088 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0726. Min Act: -0.0005

Data Index: 194664 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0666. Min Act: -0.0005

Data Index: 886023 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0005

Data Index: 340761 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0702. Min Act: -0.0005

Data Index: 133175 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0678. Min Act: -0.0005

Data Index: 6168 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0692. Min Act: -0.0005

Data Index: 923496 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0688. Min Act: -0.0005

Data Index: 931795 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0673. Min Act: -0.0005

Data Index: 1236291 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0680. Min Act: -0.0005

Data Index: 567 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0691. Min Act: -0.0005

Data Index: 1306229 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0679. Min Act: -0.0005

Data Index: 435618 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0637. Min Act: -0.0005

Data Index: 1009213 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0622. Min Act: -0.0005

Data Index: 436794 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0630. Min Act: -0.0005

Data Index: 112552 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0657. Min Act: -0.0005

Data Index: 1212476 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0656. Min Act: -0.0005

Data Index: 943576 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0666. Min Act: -0.0005

Data Index: 1132400 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0629. Min Act: -0.0005

Data Index: 464073 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0653. Min Act: -0.0005

Data Index: 910912 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0654. Min Act: -0.0005

Data Index: 474182 (C4 (Web Text))

Max Activating Token Index: 511