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

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

Neuron 1352 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0673. Min Range: -4.0673

Max Act: 4.0673. Min Act: -0.1700

Data Index: 777560 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 4.0673. Min Range: -4.0673

Max Act: 4.0673. Min Act: -0.1700

Data Index: 78068 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 4.0673. Min Range: -4.0673

Max Act: 4.0361. Min Act: -0.1700

Data Index: 1116707 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 4.0673. Min Range: -4.0673

Max Act: 4.0361. Min Act: -0.1700

Data Index: 237826 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.9735. Min Act: -0.1700

Data Index: 846547 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8797. Min Act: -0.1700

Data Index: 52579 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8484. Min Act: -0.1700

Data Index: 254687 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8172. Min Act: -0.1700

Data Index: 486801 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8172. Min Act: -0.1700

Data Index: 49826 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8172. Min Act: -0.1700

Data Index: 1076106 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7546. Min Act: -0.1700

Data Index: 1007569 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8172. Min Act: -0.1700

Data Index: 770899 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7546. Min Act: -0.1700

Data Index: 975272 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7859. Min Act: -0.1700

Data Index: 628145 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7233. Min Act: -0.1700

Data Index: 197650 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7233. Min Act: -0.1700

Data Index: 1008516 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7233. Min Act: -0.1700

Data Index: 1226578 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.6607. Min Act: -0.1700

Data Index: 529457 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.6920. Min Act: -0.1700

Data Index: 598231 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.6920. Min Act: -0.1700

Data Index: 516020 (C4 (Web Text))

Max Activating Token Index: 174