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

Dataset: Open Web Text

Neuron 685 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: 4.0261. Min Range: -4.0261

Max Act: 4.0261. Min Act: -0.1700

Data Index: 1648478 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.9648. Min Act: -0.1700

Data Index: 3590385 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.9385. Min Act: -0.1700

Data Index: 5773250 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.9486. Min Act: -0.1700

Data Index: 3104981 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.9497. Min Act: -0.1700

Data Index: 7967677 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.9360. Min Act: -0.1700

Data Index: 3492351 (Open Web Text)

Max Activating Token Index: 959

Text #6

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.9126. Min Act: -0.1700

Data Index: 493152 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.9082. Min Act: -0.1700

Data Index: 5364086 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8794. Min Act: -0.1700

Data Index: 3592084 (Open Web Text)

Max Activating Token Index: 969

Text #9

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8754. Min Act: -0.1700

Data Index: 4639661 (Open Web Text)

Max Activating Token Index: 37

Text #10

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8684. Min Act: -0.1700

Data Index: 3583174 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8689. Min Act: -0.1700

Data Index: 8808999 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8666. Min Act: -0.1700

Data Index: 2349667 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8686. Min Act: -0.1700

Data Index: 2289134 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8636. Min Act: -0.1700

Data Index: 3203876 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8646. Min Act: -0.1700

Data Index: 7965557 (Open Web Text)

Max Activating Token Index: 864

Text #16

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8753. Min Act: -0.1700

Data Index: 7502429 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8642. Min Act: -0.1700

Data Index: 2893058 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8304. Min Act: -0.1700

Data Index: 1487784 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.0261. Min Range: -4.0261

Max Act: 3.8323. Min Act: -0.1700

Data Index: 1741419 (Open Web Text)

Max Activating Token Index: 10