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

Dataset: Open Web Text

Neuron 2109 in Layer 6

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: 3.9638. Min Range: -3.9638

Max Act: 3.9638. Min Act: -0.1700

Data Index: 4775298 (Open Web Text)

Max Activating Token Index: 525

Text #1

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.7512. Min Act: -0.1700

Data Index: 775915 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.5578. Min Act: -0.1700

Data Index: 7849341 (Open Web Text)

Max Activating Token Index: 552

Text #3

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4571. Min Act: -0.1700

Data Index: 3700387 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4844. Min Act: -0.1700

Data Index: 3547457 (Open Web Text)

Max Activating Token Index: 914

Text #5

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4757. Min Act: -0.1700

Data Index: 2591033 (Open Web Text)

Max Activating Token Index: 159

Text #6

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4544. Min Act: -0.1700

Data Index: 5716311 (Open Web Text)

Max Activating Token Index: 214

Text #7

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4176. Min Act: -0.1700

Data Index: 1165567 (Open Web Text)

Max Activating Token Index: 288

Text #8

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4350. Min Act: -0.1700

Data Index: 5846104 (Open Web Text)

Max Activating Token Index: 602

Text #9

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4101. Min Act: -0.1700

Data Index: 3516951 (Open Web Text)

Max Activating Token Index: 873

Text #10

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4147. Min Act: -0.1700

Data Index: 4382001 (Open Web Text)

Max Activating Token Index: 383

Text #11

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4089. Min Act: -0.1700

Data Index: 2317084 (Open Web Text)

Max Activating Token Index: 326

Text #12

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4118. Min Act: -0.1700

Data Index: 4666691 (Open Web Text)

Max Activating Token Index: 890

Text #13

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.4136. Min Act: -0.1700

Data Index: 1643062 (Open Web Text)

Max Activating Token Index: 840

Text #14

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.3919. Min Act: -0.1700

Data Index: 6625695 (Open Web Text)

Max Activating Token Index: 724

Text #15

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.3832. Min Act: -0.1700

Data Index: 635067 (Open Web Text)

Max Activating Token Index: 128

Text #16

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.3601. Min Act: -0.1700

Data Index: 927769 (Open Web Text)

Max Activating Token Index: 682

Text #17

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.3896. Min Act: -0.1700

Data Index: 7692264 (Open Web Text)

Max Activating Token Index: 578

Text #18

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.3961. Min Act: -0.1700

Data Index: 4044803 (Open Web Text)

Max Activating Token Index: 339

Text #19

Max Range: 3.9638. Min Range: -3.9638

Max Act: 3.3574. Min Act: -0.1700

Data Index: 7334069 (Open Web Text)

Max Activating Token Index: 398