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

Dataset: Open Web Text

Neuron 608 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: 1.1666. Min Range: -1.1666

Max Act: 1.1666. Min Act: -0.1693

Data Index: 2828572 (Open Web Text)

Max Activating Token Index: 201

Text #1

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.1545. Min Act: -0.1700

Data Index: 4904961 (Open Web Text)

Max Activating Token Index: 126

Text #2

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.1320. Min Act: -0.1640

Data Index: 7664355 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.1035. Min Act: -0.1549

Data Index: 1508214 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0895. Min Act: -0.1654

Data Index: 5669078 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0927. Min Act: -0.1653

Data Index: 1285140 (Open Web Text)

Max Activating Token Index: 123

Text #6

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0813. Min Act: -0.1606

Data Index: 5275606 (Open Web Text)

Max Activating Token Index: 162

Text #7

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0846. Min Act: -0.1682

Data Index: 4716170 (Open Web Text)

Max Activating Token Index: 209

Text #8

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0728. Min Act: -0.1695

Data Index: 2912415 (Open Web Text)

Max Activating Token Index: 402

Text #9

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0545. Min Act: -0.1686

Data Index: 7005329 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0542. Min Act: -0.1440

Data Index: 5248247 (Open Web Text)

Max Activating Token Index: 96

Text #11

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0561. Min Act: -0.1673

Data Index: 1510893 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0533. Min Act: -0.1609

Data Index: 7121442 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0526. Min Act: -0.1700

Data Index: 3410539 (Open Web Text)

Max Activating Token Index: 99

Text #14

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0432. Min Act: -0.1526

Data Index: 6402101 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0473. Min Act: -0.1492

Data Index: 5499991 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0494. Min Act: -0.1686

Data Index: 1743482 (Open Web Text)

Max Activating Token Index: 308

Text #17

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0422. Min Act: -0.1601

Data Index: 2828571 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0507. Min Act: -0.1700

Data Index: 242882 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 1.1666. Min Range: -1.1666

Max Act: 1.0375. Min Act: -0.1695

Data Index: 2957208 (Open Web Text)

Max Activating Token Index: 69