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

Dataset: Open Web Text

Neuron 576 in Layer 6

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: 4.2460. Min Range: -4.2460

Max Act: 4.2271. Min Act: -0.1700

Data Index: 8531537 (Open Web Text)

Max Activating Token Index: 939

Text #1

Max Range: 4.2460. Min Range: -4.2460

Max Act: 4.2460. Min Act: -0.1700

Data Index: 1489459 (Open Web Text)

Max Activating Token Index: 241

Text #2

Max Range: 4.2460. Min Range: -4.2460

Max Act: 4.1510. Min Act: -0.1700

Data Index: 5439186 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 4.2460. Min Range: -4.2460

Max Act: 4.0777. Min Act: -0.1700

Data Index: 8576157 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 4.2460. Min Range: -4.2460

Max Act: 4.0687. Min Act: -0.1700

Data Index: 6992184 (Open Web Text)

Max Activating Token Index: 158

Text #5

Max Range: 4.2460. Min Range: -4.2460

Max Act: 4.0398. Min Act: -0.1700

Data Index: 8236252 (Open Web Text)

Max Activating Token Index: 461

Text #6

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.9902. Min Act: -0.1700

Data Index: 2710641 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 4.2460. Min Range: -4.2460

Max Act: 4.0049. Min Act: -0.1700

Data Index: 6433733 (Open Web Text)

Max Activating Token Index: 408

Text #8

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.9900. Min Act: -0.1700

Data Index: 4556188 (Open Web Text)

Max Activating Token Index: 658

Text #9

Max Range: 4.2460. Min Range: -4.2460

Max Act: 4.0060. Min Act: -0.1700

Data Index: 3018752 (Open Web Text)

Max Activating Token Index: 541

Text #10

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.9413. Min Act: -0.1700

Data Index: 8543611 (Open Web Text)

Max Activating Token Index: 670

Text #11

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.9619. Min Act: -0.1700

Data Index: 8319581 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.9047. Min Act: -0.1700

Data Index: 6237642 (Open Web Text)

Max Activating Token Index: 825

Text #13

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.9232. Min Act: -0.1700

Data Index: 7447967 (Open Web Text)

Max Activating Token Index: 414

Text #14

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.8850. Min Act: -0.1700

Data Index: 1317065 (Open Web Text)

Max Activating Token Index: 222

Text #15

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.9201. Min Act: -0.1700

Data Index: 999118 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.8831. Min Act: -0.1700

Data Index: 1200815 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.8753. Min Act: -0.1700

Data Index: 6944483 (Open Web Text)

Max Activating Token Index: 875

Text #18

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.8650. Min Act: -0.1700

Data Index: 8501925 (Open Web Text)

Max Activating Token Index: 588

Text #19

Max Range: 4.2460. Min Range: -4.2460

Max Act: 3.8978. Min Act: -0.1700

Data Index: 2735210 (Open Web Text)

Max Activating Token Index: 448