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

Dataset: Open Web Text

Neuron 2103 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: 3.2950. Min Range: -3.2950

Max Act: 3.2950. Min Act: -0.1700

Data Index: 8462808 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.2284. Min Act: -0.1700

Data Index: 503944 (Open Web Text)

Max Activating Token Index: 885

Text #2

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.1980. Min Act: -0.1700

Data Index: 4933866 (Open Web Text)

Max Activating Token Index: 901

Text #3

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.1739. Min Act: -0.1700

Data Index: 4342102 (Open Web Text)

Max Activating Token Index: 920

Text #4

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.1233. Min Act: -0.1700

Data Index: 4574096 (Open Web Text)

Max Activating Token Index: 334

Text #5

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0868. Min Act: -0.1700

Data Index: 7040595 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0790. Min Act: -0.1700

Data Index: 2326017 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0720. Min Act: -0.1700

Data Index: 1416766 (Open Web Text)

Max Activating Token Index: 880

Text #8

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0871. Min Act: -0.1700

Data Index: 3485743 (Open Web Text)

Max Activating Token Index: 419

Text #9

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0700. Min Act: -0.1700

Data Index: 523837 (Open Web Text)

Max Activating Token Index: 619

Text #10

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0818. Min Act: -0.1700

Data Index: 6118303 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0697. Min Act: -0.1700

Data Index: 8799491 (Open Web Text)

Max Activating Token Index: 238

Text #12

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0339. Min Act: -0.1700

Data Index: 2240149 (Open Web Text)

Max Activating Token Index: 366

Text #13

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0602. Min Act: -0.1700

Data Index: 7414842 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0137. Min Act: -0.1700

Data Index: 3277035 (Open Web Text)

Max Activating Token Index: 84

Text #15

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0120. Min Act: -0.1700

Data Index: 7881388 (Open Web Text)

Max Activating Token Index: 759

Text #16

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0190. Min Act: -0.1700

Data Index: 3955982 (Open Web Text)

Max Activating Token Index: 446

Text #17

Max Range: 3.2950. Min Range: -3.2950

Max Act: 3.0085. Min Act: -0.1700

Data Index: 1389686 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 3.2950. Min Range: -3.2950

Max Act: 2.9893. Min Act: -0.1700

Data Index: 6513777 (Open Web Text)

Max Activating Token Index: 777

Text #19

Max Range: 3.2950. Min Range: -3.2950

Max Act: 2.9965. Min Act: -0.1700

Data Index: 6162840 (Open Web Text)

Max Activating Token Index: 410