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

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

Neuron 1703 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: 0.0768. Min Range: -0.0768

Max Act: 0.0753. Min Act: -0.0002

Data Index: 847473 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0741. Min Act: -0.0002

Data Index: 119208 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0002

Data Index: 240254 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0720. Min Act: -0.0002

Data Index: 215628 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1132572 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0666. Min Act: -0.0002

Data Index: 383578 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0676. Min Act: -0.0002

Data Index: 935033 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1143327 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1253481 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1210854 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0642. Min Act: -0.0002

Data Index: 440277 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1084028 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0644. Min Act: -0.0002

Data Index: 164001 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1041702 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0630. Min Act: -0.0002

Data Index: 119102 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0619. Min Act: -0.0002

Data Index: 813405 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1157767 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0612. Min Act: -0.0002

Data Index: 328735 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0617. Min Act: -0.0002

Data Index: 909608 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0619. Min Act: -0.0002

Data Index: 959462 (C4 (Web Text))

Max Activating Token Index: 748