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

Dataset: Open Web Text

Neuron 2453 in Layer 0

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: 4.6837. Min Range: -4.6837

Max Act: 4.6837. Min Act: -0.1700

Data Index: 4621078 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.5922. Min Act: -0.1700

Data Index: 8609776 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.5432. Min Act: -0.1700

Data Index: 7804332 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.5367. Min Act: -0.1700

Data Index: 3526117 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4933. Min Act: -0.1700

Data Index: 1212151 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4779. Min Act: -0.1700

Data Index: 1816382 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.5102. Min Act: -0.1700

Data Index: 1922055 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.5081. Min Act: -0.1700

Data Index: 7211710 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.5083. Min Act: -0.1700

Data Index: 2754336 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4947. Min Act: -0.1700

Data Index: 8791508 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4572. Min Act: -0.1700

Data Index: 7627533 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4572. Min Act: -0.1700

Data Index: 3827952 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4644. Min Act: -0.1700

Data Index: 8371689 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4463. Min Act: -0.1700

Data Index: 8259777 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4700. Min Act: -0.1700

Data Index: 5286517 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4493. Min Act: -0.1700

Data Index: 5256447 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4586. Min Act: -0.1700

Data Index: 1881691 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4789. Min Act: -0.1700

Data Index: 7113168 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4666. Min Act: -0.1700

Data Index: 6042808 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.6837. Min Range: -4.6837

Max Act: 4.4706. Min Act: -0.1700

Data Index: 4274518 (Open Web Text)

Max Activating Token Index: 3