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

Dataset: Open Web Text

Neuron 530 in Layer 3

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: 2.5333. Min Range: -2.5333

Max Act: 2.5333. Min Act: -0.1700

Data Index: 3158001 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.5331. Min Act: -0.1700

Data Index: 2952523 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.5040. Min Act: -0.1700

Data Index: 8487046 (Open Web Text)

Max Activating Token Index: 662

Text #3

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.4448. Min Act: -0.1700

Data Index: 1688652 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.4030. Min Act: -0.1700

Data Index: 813537 (Open Web Text)

Max Activating Token Index: 501

Text #5

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.4097. Min Act: -0.1700

Data Index: 5517972 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.4109. Min Act: -0.1700

Data Index: 2856171 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3972. Min Act: -0.1700

Data Index: 5834335 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.4111. Min Act: -0.1700

Data Index: 2595649 (Open Web Text)

Max Activating Token Index: 525

Text #9

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3996. Min Act: -0.1700

Data Index: 5102661 (Open Web Text)

Max Activating Token Index: 721

Text #10

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3822. Min Act: -0.1700

Data Index: 3709804 (Open Web Text)

Max Activating Token Index: 377

Text #11

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3482. Min Act: -0.1700

Data Index: 691633 (Open Web Text)

Max Activating Token Index: 156

Text #12

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3721. Min Act: -0.1700

Data Index: 7514972 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3730. Min Act: -0.1700

Data Index: 3279226 (Open Web Text)

Max Activating Token Index: 287

Text #14

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3498. Min Act: -0.1700

Data Index: 712386 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3710. Min Act: -0.1700

Data Index: 814442 (Open Web Text)

Max Activating Token Index: 538

Text #16

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3709. Min Act: -0.1700

Data Index: 4482917 (Open Web Text)

Max Activating Token Index: 175

Text #17

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3566. Min Act: -0.1700

Data Index: 3304687 (Open Web Text)

Max Activating Token Index: 782

Text #18

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3583. Min Act: -0.1700

Data Index: 6215624 (Open Web Text)

Max Activating Token Index: 693

Text #19

Max Range: 2.5333. Min Range: -2.5333

Max Act: 2.3618. Min Act: -0.1700

Data Index: 3644820 (Open Web Text)

Max Activating Token Index: 3