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

Dataset: Open Web Text

Neuron 992 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: 3.2921. Min Range: -3.2921

Max Act: 3.2759. Min Act: -0.1700

Data Index: 901641 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.2921. Min Act: -0.1700

Data Index: 901639 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1966. Min Act: -0.1700

Data Index: 901645 (Open Web Text)

Max Activating Token Index: 645

Text #3

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.2092. Min Act: -0.1700

Data Index: 2215417 (Open Web Text)

Max Activating Token Index: 917

Text #4

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1710. Min Act: -0.1700

Data Index: 3026429 (Open Web Text)

Max Activating Token Index: 674

Text #5

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1597. Min Act: -0.1700

Data Index: 3078756 (Open Web Text)

Max Activating Token Index: 838

Text #6

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1137. Min Act: -0.1700

Data Index: 7654536 (Open Web Text)

Max Activating Token Index: 372

Text #7

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1378. Min Act: -0.1700

Data Index: 4696745 (Open Web Text)

Max Activating Token Index: 530

Text #8

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1188. Min Act: -0.1700

Data Index: 1065491 (Open Web Text)

Max Activating Token Index: 701

Text #9

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.1002. Min Act: -0.1700

Data Index: 1586569 (Open Web Text)

Max Activating Token Index: 763

Text #10

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0922. Min Act: -0.1700

Data Index: 8439560 (Open Web Text)

Max Activating Token Index: 449

Text #11

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0701. Min Act: -0.1700

Data Index: 86408 (Open Web Text)

Max Activating Token Index: 385

Text #12

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0669. Min Act: -0.1700

Data Index: 1877053 (Open Web Text)

Max Activating Token Index: 584

Text #13

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0657. Min Act: -0.1700

Data Index: 7317072 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0481. Min Act: -0.1700

Data Index: 5793651 (Open Web Text)

Max Activating Token Index: 318

Text #15

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0607. Min Act: -0.1700

Data Index: 4449654 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0657. Min Act: -0.1700

Data Index: 2861516 (Open Web Text)

Max Activating Token Index: 398

Text #17

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0525. Min Act: -0.1700

Data Index: 6352671 (Open Web Text)

Max Activating Token Index: 912

Text #18

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0525. Min Act: -0.1700

Data Index: 5069286 (Open Web Text)

Max Activating Token Index: 444

Text #19

Max Range: 3.2921. Min Range: -3.2921

Max Act: 3.0390. Min Act: -0.1700

Data Index: 5868825 (Open Web Text)

Max Activating Token Index: 779