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

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

Neuron 1296 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0006

Data Index: 461732 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0960. Min Act: -0.0006

Data Index: 355079 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0852. Min Act: -0.0006

Data Index: 238803 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0759. Min Act: -0.0006

Data Index: 1345578 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0731. Min Act: -0.0006

Data Index: 920581 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0699. Min Act: -0.0006

Data Index: 645598 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0694. Min Act: -0.0006

Data Index: 1111397 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0665. Min Act: -0.0006

Data Index: 389381 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0682. Min Act: -0.0006

Data Index: 840027 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0660. Min Act: -0.0006

Data Index: 939713 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0654. Min Act: -0.0006

Data Index: 1236540 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0648. Min Act: -0.0006

Data Index: 562597 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0648. Min Act: -0.0006

Data Index: 191627 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0631. Min Act: -0.0006

Data Index: 609871 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0650. Min Act: -0.0006

Data Index: 510643 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0651. Min Act: -0.0006

Data Index: 1158805 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0651. Min Act: -0.0006

Data Index: 663793 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0638. Min Act: -0.0006

Data Index: 289941 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0617. Min Act: -0.0006

Data Index: 442341 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0607. Min Act: -0.0006

Data Index: 1283807 (C4 (Web Text))

Max Activating Token Index: 189