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

Dataset: Open Web Text

Neuron 1274 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: 4.7976. Min Range: -4.7976

Max Act: 4.7870. Min Act: -0.1700

Data Index: 844417 (Open Web Text)

Max Activating Token Index: 634

Text #1

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.7710. Min Act: -0.1700

Data Index: 1164382 (Open Web Text)

Max Activating Token Index: 170

Text #2

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.7976. Min Act: -0.1700

Data Index: 7399064 (Open Web Text)

Max Activating Token Index: 660

Text #3

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.6011. Min Act: -0.1700

Data Index: 2854132 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.7045. Min Act: -0.1700

Data Index: 1966658 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.6911. Min Act: -0.1700

Data Index: 6742976 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.6250. Min Act: -0.1700

Data Index: 7416349 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.6612. Min Act: -0.1700

Data Index: 4621868 (Open Web Text)

Max Activating Token Index: 520

Text #8

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.5914. Min Act: -0.1700

Data Index: 446338 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.4989. Min Act: -0.1700

Data Index: 3826371 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.6029. Min Act: -0.1700

Data Index: 7244052 (Open Web Text)

Max Activating Token Index: 893

Text #11

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.5257. Min Act: -0.1700

Data Index: 5722502 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.5020. Min Act: -0.1700

Data Index: 5800207 (Open Web Text)

Max Activating Token Index: 332

Text #13

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.5653. Min Act: -0.1700

Data Index: 7397608 (Open Web Text)

Max Activating Token Index: 154

Text #14

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.5131. Min Act: -0.1700

Data Index: 6290944 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.5570. Min Act: -0.1700

Data Index: 567227 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.5445. Min Act: -0.1700

Data Index: 5478392 (Open Web Text)

Max Activating Token Index: 392

Text #17

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.5758. Min Act: -0.1700

Data Index: 6993357 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.4733. Min Act: -0.1700

Data Index: 7531004 (Open Web Text)

Max Activating Token Index: 772

Text #19

Max Range: 4.7976. Min Range: -4.7976

Max Act: 4.5586. Min Act: -0.1700

Data Index: 2928798 (Open Web Text)

Max Activating Token Index: 959