Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2739 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0003

Data Index: 705670 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0628. Min Act: -0.0002

Data Index: 958088 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0664. Min Act: -0.0003

Data Index: 544708 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0634. Min Act: -0.0003

Data Index: 361152 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0663. Min Act: -0.0002

Data Index: 772608 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0629. Min Act: -0.0003

Data Index: 890938 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1017844 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1256826 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0607. Min Act: -0.0002

Data Index: 726607 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0625. Min Act: -0.0003

Data Index: 924820 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0596. Min Act: -0.0002

Data Index: 111452 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0608. Min Act: -0.0002

Data Index: 782084 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0581. Min Act: -0.0003

Data Index: 208722 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0582. Min Act: -0.0003

Data Index: 646380 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1384092 (Python Code)

Max Activating Token Index: 310

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0595. Min Act: -0.0003

Data Index: 39156 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1009095 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0579. Min Act: -0.0003

Data Index: 375668 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0580. Min Act: -0.0003

Data Index: 109695 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0550. Min Act: -0.0002

Data Index: 999044 (C4 (Web Text))

Max Activating Token Index: 377