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

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

Neuron 743 in Layer 1

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: 0.0700. Min Range: -0.0700

Max Act: 0.0684. Min Act: -0.0002

Data Index: 888390 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0683. Min Act: -0.0002

Data Index: 561100 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0684. Min Act: -0.0002

Data Index: 187120 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0700. Min Act: -0.0002

Data Index: 538160 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0658. Min Act: -0.0002

Data Index: 866330 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1099022 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1306637 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1031286 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1266905 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1319201 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0634. Min Act: -0.0002

Data Index: 612181 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0634. Min Act: -0.0002

Data Index: 552058 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0628. Min Act: -0.0002

Data Index: 384090 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1290039 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0619. Min Act: -0.0002

Data Index: 775452 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0654. Min Act: -0.0002

Data Index: 903809 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0625. Min Act: -0.0002

Data Index: 475318 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1161812 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0646. Min Act: -0.0002

Data Index: 780462 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.0700. Min Range: -0.0700

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1333986 (C4 (Web Text))

Max Activating Token Index: 714