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

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

Neuron 2611 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.7022. Min Act: -0.0001

Data Index: 1417842 (Python Code)

Max Activating Token Index: 886

Text #1

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.6282. Min Act: -0.0001

Data Index: 20888 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5759. Min Act: -0.0000

Data Index: 659146 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5793. Min Act: -0.0001

Data Index: 1573546 (Python Code)

Max Activating Token Index: 705

Text #4

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5386. Min Act: -0.0000

Data Index: 499948 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4994. Min Act: -0.0001

Data Index: 1591888 (Python Code)

Max Activating Token Index: 624

Text #6

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5090. Min Act: -0.0001

Data Index: 1540270 (Python Code)

Max Activating Token Index: 370

Text #7

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5142. Min Act: -0.0001

Data Index: 1494936 (Python Code)

Max Activating Token Index: 967

Text #8

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4943. Min Act: -0.0001

Data Index: 1414257 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.5080. Min Act: -0.0001

Data Index: 1421438 (Python Code)

Max Activating Token Index: 198

Text #10

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4869. Min Act: -0.0001

Data Index: 1553559 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4848. Min Act: -0.0001

Data Index: 1511848 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4807. Min Act: -0.0001

Data Index: 1070917 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4809. Min Act: -0.0000

Data Index: 643305 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4746. Min Act: -0.0001

Data Index: 1377022 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4571. Min Act: -0.0001

Data Index: 1460366 (Python Code)

Max Activating Token Index: 272

Text #16

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1086396 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4645. Min Act: -0.0001

Data Index: 1626854 (Python Code)

Max Activating Token Index: 777

Text #18

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4649. Min Act: -0.0001

Data Index: 1385539 (Python Code)

Max Activating Token Index: 680

Text #19

Max Range: 0.7022. Min Range: -0.7022

Max Act: 0.4719. Min Act: -0.0001

Data Index: 1404345 (Python Code)

Max Activating Token Index: 596