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

Dataset: Open Web Text

Neuron 1439 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: 1.7413. Min Range: -1.7413

Max Act: 1.7409. Min Act: -0.1700

Data Index: 8822647 (Open Web Text)

Max Activating Token Index: 560

Text #1

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.7413. Min Act: -0.1700

Data Index: 6216152 (Open Web Text)

Max Activating Token Index: 254

Text #2

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6958. Min Act: -0.1700

Data Index: 6807117 (Open Web Text)

Max Activating Token Index: 729

Text #3

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6828. Min Act: -0.1700

Data Index: 2316731 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6849. Min Act: -0.1700

Data Index: 3197745 (Open Web Text)

Max Activating Token Index: 968

Text #5

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6935. Min Act: -0.1700

Data Index: 8466315 (Open Web Text)

Max Activating Token Index: 229

Text #6

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6774. Min Act: -0.1700

Data Index: 4563893 (Open Web Text)

Max Activating Token Index: 51

Text #7

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6782. Min Act: -0.1700

Data Index: 5724244 (Open Web Text)

Max Activating Token Index: 145

Text #8

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6709. Min Act: -0.1700

Data Index: 6122011 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6711. Min Act: -0.1698

Data Index: 4351846 (Open Web Text)

Max Activating Token Index: 746

Text #10

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6696. Min Act: -0.1700

Data Index: 1913420 (Open Web Text)

Max Activating Token Index: 845

Text #11

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6653. Min Act: -0.1698

Data Index: 6456380 (Open Web Text)

Max Activating Token Index: 360

Text #12

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6761. Min Act: -0.1700

Data Index: 5803259 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6771. Min Act: -0.1700

Data Index: 4176745 (Open Web Text)

Max Activating Token Index: 128

Text #14

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6607. Min Act: -0.1700

Data Index: 199108 (Open Web Text)

Max Activating Token Index: 674

Text #15

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6572. Min Act: -0.1700

Data Index: 8371177 (Open Web Text)

Max Activating Token Index: 890

Text #16

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6592. Min Act: -0.1700

Data Index: 8559263 (Open Web Text)

Max Activating Token Index: 188

Text #17

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6470. Min Act: -0.1700

Data Index: 4469250 (Open Web Text)

Max Activating Token Index: 215

Text #18

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6549. Min Act: -0.1700

Data Index: 4573632 (Open Web Text)

Max Activating Token Index: 246

Text #19

Max Range: 1.7413. Min Range: -1.7413

Max Act: 1.6516. Min Act: -0.1700

Data Index: 7867647 (Open Web Text)

Max Activating Token Index: 256