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

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

Neuron 1395 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1027633 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.7508. Min Act: -0.0000

Data Index: 271459 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.7687. Min Act: -0.0001

Data Index: 342536 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6150. Min Act: -0.0001

Data Index: 1142196 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5741. Min Act: -0.0001

Data Index: 1213710 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5898. Min Act: -0.0001

Data Index: 630371 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5621. Min Act: -0.0001

Data Index: 808528 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5386. Min Act: -0.0000

Data Index: 415689 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5475. Min Act: -0.0001

Data Index: 956059 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5044. Min Act: -0.0001

Data Index: 1025018 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5193. Min Act: -0.0001

Data Index: 180203 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4893. Min Act: -0.0000

Data Index: 944937 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5006. Min Act: -0.0000

Data Index: 170751 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4776. Min Act: -0.0001

Data Index: 536574 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4783. Min Act: -0.0001

Data Index: 808674 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4755. Min Act: -0.0001

Data Index: 327163 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4954. Min Act: -0.0001

Data Index: 90627 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4665. Min Act: -0.0001

Data Index: 107620 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4618. Min Act: -0.0001

Data Index: 604102 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4720. Min Act: -0.0001

Data Index: 449758 (C4 (Web Text))

Max Activating Token Index: 763