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

Dataset: Open Web Text

Neuron 508 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: 3.6263. Min Range: -3.6263

Max Act: 3.6263. Min Act: -0.1700

Data Index: 8056395 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.5551. Min Act: -0.1700

Data Index: 1121241 (Open Web Text)

Max Activating Token Index: 690

Text #2

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.5442. Min Act: -0.1700

Data Index: 7834622 (Open Web Text)

Max Activating Token Index: 900

Text #3

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4869. Min Act: -0.1700

Data Index: 6625593 (Open Web Text)

Max Activating Token Index: 150

Text #4

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4457. Min Act: -0.1700

Data Index: 4268031 (Open Web Text)

Max Activating Token Index: 435

Text #5

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4526. Min Act: -0.1700

Data Index: 689481 (Open Web Text)

Max Activating Token Index: 903

Text #6

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4167. Min Act: -0.1700

Data Index: 3262815 (Open Web Text)

Max Activating Token Index: 732

Text #7

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3608. Min Act: -0.1700

Data Index: 5621245 (Open Web Text)

Max Activating Token Index: 405

Text #8

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4287. Min Act: -0.1700

Data Index: 989365 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4444. Min Act: -0.1700

Data Index: 5982043 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4342. Min Act: -0.1700

Data Index: 2987096 (Open Web Text)

Max Activating Token Index: 225

Text #11

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3871. Min Act: -0.1700

Data Index: 6823591 (Open Web Text)

Max Activating Token Index: 280

Text #12

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3994. Min Act: -0.1700

Data Index: 5335731 (Open Web Text)

Max Activating Token Index: 944

Text #13

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3899. Min Act: -0.1700

Data Index: 1742503 (Open Web Text)

Max Activating Token Index: 818

Text #14

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3752. Min Act: -0.1700

Data Index: 123576 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4024. Min Act: -0.1700

Data Index: 1170035 (Open Web Text)

Max Activating Token Index: 957

Text #16

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3511. Min Act: -0.1700

Data Index: 5947774 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4127. Min Act: -0.1700

Data Index: 2979035 (Open Web Text)

Max Activating Token Index: 923

Text #18

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3878. Min Act: -0.1700

Data Index: 1510455 (Open Web Text)

Max Activating Token Index: 1000

Text #19

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4056. Min Act: -0.1700

Data Index: 4886159 (Open Web Text)

Max Activating Token Index: 446