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

Dataset: Open Web Text

Neuron 712 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: 3.7100. Min Range: -3.7100

Max Act: 3.7100. Min Act: -0.1700

Data Index: 8562160 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.5520. Min Act: -0.1700

Data Index: 8647653 (Open Web Text)

Max Activating Token Index: 129

Text #2

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.5287. Min Act: -0.1700

Data Index: 6439263 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.5494. Min Act: -0.1700

Data Index: 7543609 (Open Web Text)

Max Activating Token Index: 645

Text #4

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.5077. Min Act: -0.1700

Data Index: 7778032 (Open Web Text)

Max Activating Token Index: 928

Text #5

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4970. Min Act: -0.1700

Data Index: 8670075 (Open Web Text)

Max Activating Token Index: 116

Text #6

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4770. Min Act: -0.1700

Data Index: 7059730 (Open Web Text)

Max Activating Token Index: 75

Text #7

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4759. Min Act: -0.1700

Data Index: 238828 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4533. Min Act: -0.1700

Data Index: 6506727 (Open Web Text)

Max Activating Token Index: 625

Text #9

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4791. Min Act: -0.1700

Data Index: 328486 (Open Web Text)

Max Activating Token Index: 208

Text #10

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4750. Min Act: -0.1700

Data Index: 7151928 (Open Web Text)

Max Activating Token Index: 145

Text #11

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4642. Min Act: -0.1700

Data Index: 8659588 (Open Web Text)

Max Activating Token Index: 587

Text #12

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4497. Min Act: -0.1700

Data Index: 3755331 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4509. Min Act: -0.1700

Data Index: 5200467 (Open Web Text)

Max Activating Token Index: 739

Text #14

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4454. Min Act: -0.1700

Data Index: 6239891 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4368. Min Act: -0.1700

Data Index: 3752818 (Open Web Text)

Max Activating Token Index: 184

Text #16

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4154. Min Act: -0.1700

Data Index: 1775456 (Open Web Text)

Max Activating Token Index: 638

Text #17

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4389. Min Act: -0.1700

Data Index: 2136450 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4117. Min Act: -0.1700

Data Index: 60212 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.4045. Min Act: -0.1700

Data Index: 8438427 (Open Web Text)

Max Activating Token Index: 1008