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

Dataset: Open Web Text

Neuron 2827 in Layer 1

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: 1.8401. Min Range: -1.8401

Max Act: 1.8401. Min Act: -0.1700

Data Index: 6926428 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 380724 (Open Web Text)

Max Activating Token Index: 1

Text #2

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 441899 (Open Web Text)

Max Activating Token Index: 1

Text #3

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8062. Min Act: -0.1700

Data Index: 133752 (Open Web Text)

Max Activating Token Index: 1

Text #4

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8187. Min Act: -0.1700

Data Index: 132771 (Open Web Text)

Max Activating Token Index: 1

Text #5

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 440064 (Open Web Text)

Max Activating Token Index: 1

Text #6

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 411234 (Open Web Text)

Max Activating Token Index: 1

Text #7

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8275. Min Act: -0.1700

Data Index: 37497 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 129080 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 391034 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8275. Min Act: -0.1700

Data Index: 387262 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8062. Min Act: -0.1700

Data Index: 352922 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 481528 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 473552 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8275. Min Act: -0.1700

Data Index: 201752 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 86503 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 74278 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8275. Min Act: -0.1700

Data Index: 25453 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8275. Min Act: -0.1700

Data Index: 64358 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 1.8401. Min Range: -1.8401

Max Act: 1.8112. Min Act: -0.1700

Data Index: 172622 (Open Web Text)

Max Activating Token Index: 1