Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 554 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0773. Min Range: -4.0773

Max Act: 4.0763. Min Act: -0.1700

Data Index: 1027611 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 4.0773. Min Range: -4.0773

Max Act: 4.0773. Min Act: -0.1700

Data Index: 4123227 (Open Web Text)

Max Activating Token Index: 407

Text #2

Max Range: 4.0773. Min Range: -4.0773

Max Act: 4.0654. Min Act: -0.1700

Data Index: 3015424 (Open Web Text)

Max Activating Token Index: 432

Text #3

Max Range: 4.0773. Min Range: -4.0773

Max Act: 4.0313. Min Act: -0.1700

Data Index: 79385 (Open Web Text)

Max Activating Token Index: 42

Text #4

Max Range: 4.0773. Min Range: -4.0773

Max Act: 4.0365. Min Act: -0.1700

Data Index: 2624746 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 4.0773. Min Range: -4.0773

Max Act: 4.0082. Min Act: -0.1700

Data Index: 3265103 (Open Web Text)

Max Activating Token Index: 454

Text #6

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9769. Min Act: -0.1700

Data Index: 2008415 (Open Web Text)

Max Activating Token Index: 250

Text #7

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9690. Min Act: -0.1700

Data Index: 8829622 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9776. Min Act: -0.1700

Data Index: 8652024 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9837. Min Act: -0.1700

Data Index: 6522543 (Open Web Text)

Max Activating Token Index: 497

Text #10

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9660. Min Act: -0.1700

Data Index: 6168348 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9917. Min Act: -0.1700

Data Index: 809212 (Open Web Text)

Max Activating Token Index: 994

Text #12

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9952. Min Act: -0.1700

Data Index: 8571435 (Open Web Text)

Max Activating Token Index: 260

Text #13

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9565. Min Act: -0.1700

Data Index: 561481 (Open Web Text)

Max Activating Token Index: 610

Text #14

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9903. Min Act: -0.1700

Data Index: 8470965 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9867. Min Act: -0.1700

Data Index: 4447078 (Open Web Text)

Max Activating Token Index: 256

Text #16

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9572. Min Act: -0.1700

Data Index: 7286812 (Open Web Text)

Max Activating Token Index: 789

Text #17

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9299. Min Act: -0.1700

Data Index: 7826847 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9289. Min Act: -0.1700

Data Index: 8073757 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 4.0773. Min Range: -4.0773

Max Act: 3.9784. Min Act: -0.1700

Data Index: 4408870 (Open Web Text)

Max Activating Token Index: 688