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

Dataset: Open Web Text

Neuron 1739 in Layer 2

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: 1.9882. Min Range: -1.9882

Max Act: 1.9882. Min Act: -0.1700

Data Index: 7456082 (Open Web Text)

Max Activating Token Index: 831

Text #1

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9784. Min Act: -0.1649

Data Index: 314694 (Open Web Text)

Max Activating Token Index: 731

Text #2

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9777. Min Act: -0.1700

Data Index: 6612764 (Open Web Text)

Max Activating Token Index: 217

Text #3

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9423. Min Act: -0.1700

Data Index: 5756631 (Open Web Text)

Max Activating Token Index: 913

Text #4

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9402. Min Act: -0.1700

Data Index: 5789447 (Open Web Text)

Max Activating Token Index: 294

Text #5

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9168. Min Act: -0.1700

Data Index: 1834502 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9167. Min Act: -0.1700

Data Index: 7969955 (Open Web Text)

Max Activating Token Index: 381

Text #7

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9193. Min Act: -0.1700

Data Index: 1395278 (Open Web Text)

Max Activating Token Index: 763

Text #8

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9097. Min Act: -0.1700

Data Index: 2673800 (Open Web Text)

Max Activating Token Index: 288

Text #9

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9096. Min Act: -0.1700

Data Index: 4673928 (Open Web Text)

Max Activating Token Index: 191

Text #10

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9051. Min Act: -0.1699

Data Index: 6135371 (Open Web Text)

Max Activating Token Index: 128

Text #11

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9016. Min Act: -0.1699

Data Index: 8530650 (Open Web Text)

Max Activating Token Index: 525

Text #12

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8987. Min Act: -0.1699

Data Index: 6279259 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8931. Min Act: -0.1700

Data Index: 4166322 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8898. Min Act: -0.1700

Data Index: 5978469 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8946. Min Act: -0.1700

Data Index: 982964 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8762. Min Act: -0.1671

Data Index: 574973 (Open Web Text)

Max Activating Token Index: 371

Text #17

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8766. Min Act: -0.1700

Data Index: 5351996 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8731. Min Act: -0.1664

Data Index: 7616073 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8735. Min Act: -0.1700

Data Index: 4745230 (Open Web Text)

Max Activating Token Index: 862