Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1208 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1000552 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1192151 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1332164 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0707. Min Act: -0.0002

Data Index: 848504 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1331411 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0704. Min Act: -0.0001

Data Index: 186443 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0689. Min Act: -0.0001

Data Index: 596891 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1044010 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0678. Min Act: -0.0001

Data Index: 433253 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1637552 (Python Code)

Max Activating Token Index: 498

Text #10

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0682. Min Act: -0.0001

Data Index: 73812 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0677. Min Act: -0.0001

Data Index: 676073 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0678. Min Act: -0.0001

Data Index: 428087 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0667. Min Act: -0.0001

Data Index: 247294 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0685. Min Act: -0.0001

Data Index: 164065 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0673. Min Act: -0.0001

Data Index: 850755 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0673. Min Act: -0.0001

Data Index: 937831 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0680. Min Act: -0.0001

Data Index: 813219 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0670. Min Act: -0.0001

Data Index: 810000 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0671. Min Act: -0.0002

Data Index: 113365 (C4 (Web Text))

Max Activating Token Index: 372