Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4074 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1194118 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0711. Min Act: -0.0001

Data Index: 780450 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0696. Min Act: -0.0001

Data Index: 353530 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0688. Min Act: -0.0001

Data Index: 599732 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0736. Min Act: -0.0001

Data Index: 963177 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1046627 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0656. Min Act: -0.0001

Data Index: 980687 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0698. Min Act: -0.0001

Data Index: 1193102 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0675. Min Act: -0.0001

Data Index: 580087 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0688. Min Act: -0.0001

Data Index: 694594 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1311496 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0672. Min Act: -0.0001

Data Index: 82504 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0713. Min Act: -0.0001

Data Index: 945922 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0691. Min Act: -0.0001

Data Index: 381157 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1004430 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0661. Min Act: -0.0001

Data Index: 96754 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0680. Min Act: -0.0001

Data Index: 887698 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0656. Min Act: -0.0001

Data Index: 842100 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1178633 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0650. Min Act: -0.0001

Data Index: 926721 (C4 (Web Text))

Max Activating Token Index: 165