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

Dataset: Open Web Text

Neuron 987 in Layer 5

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: 3.1821. Min Range: -3.1821

Max Act: 3.1666. Min Act: -0.1700

Data Index: 5014745 (Open Web Text)

Max Activating Token Index: 45

Text #1

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.1821. Min Act: -0.1700

Data Index: 1781837 (Open Web Text)

Max Activating Token Index: 925

Text #2

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.1427. Min Act: -0.1700

Data Index: 5108747 (Open Web Text)

Max Activating Token Index: 233

Text #3

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.1595. Min Act: -0.1700

Data Index: 6302124 (Open Web Text)

Max Activating Token Index: 949

Text #4

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.1339. Min Act: -0.1700

Data Index: 1143087 (Open Web Text)

Max Activating Token Index: 163

Text #5

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.1041. Min Act: -0.1700

Data Index: 2527357 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.1057. Min Act: -0.1700

Data Index: 2122570 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0815. Min Act: -0.1700

Data Index: 2922998 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0670. Min Act: -0.1700

Data Index: 8383681 (Open Web Text)

Max Activating Token Index: 50

Text #9

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0766. Min Act: -0.1700

Data Index: 154665 (Open Web Text)

Max Activating Token Index: 916

Text #10

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0689. Min Act: -0.1700

Data Index: 7660013 (Open Web Text)

Max Activating Token Index: 874

Text #11

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0792. Min Act: -0.1700

Data Index: 4062312 (Open Web Text)

Max Activating Token Index: 652

Text #12

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0498. Min Act: -0.1700

Data Index: 1107053 (Open Web Text)

Max Activating Token Index: 569

Text #13

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0515. Min Act: -0.1700

Data Index: 7540057 (Open Web Text)

Max Activating Token Index: 497

Text #14

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0430. Min Act: -0.1700

Data Index: 6014417 (Open Web Text)

Max Activating Token Index: 413

Text #15

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0582. Min Act: -0.1700

Data Index: 5100808 (Open Web Text)

Max Activating Token Index: 807

Text #16

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0348. Min Act: -0.1700

Data Index: 4069790 (Open Web Text)

Max Activating Token Index: 282

Text #17

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0327. Min Act: -0.1700

Data Index: 3427478 (Open Web Text)

Max Activating Token Index: 964

Text #18

Max Range: 3.1821. Min Range: -3.1821

Max Act: 2.9853. Min Act: -0.1700

Data Index: 7489618 (Open Web Text)

Max Activating Token Index: 473

Text #19

Max Range: 3.1821. Min Range: -3.1821

Max Act: 3.0190. Min Act: -0.1700

Data Index: 7520405 (Open Web Text)

Max Activating Token Index: 127