Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 201 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1508. Min Range: -3.1508
Max Act: 3.1508. Min Act: -0.1700
Data Index: 7128648 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1508. Min Range: -3.1508
Max Act: 3.0878. Min Act: -0.1700
Data Index: 5839642 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1508. Min Range: -3.1508
Max Act: 3.1036. Min Act: -0.1700
Data Index: 3530425 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1508. Min Range: -3.1508
Max Act: 3.0878. Min Act: -0.1700
Data Index: 6058620 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1508. Min Range: -3.1508
Max Act: 3.0563. Min Act: -0.1700
Data Index: 3913497 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1508. Min Range: -3.1508
Max Act: 3.0405. Min Act: -0.1700
Data Index: 2366138 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.9773. Min Act: -0.1700
Data Index: 8350795 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.9615. Min Act: -0.1700
Data Index: 3225857 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.9615. Min Act: -0.1700
Data Index: 4385737 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.9456. Min Act: -0.1700
Data Index: 8397220 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.9615. Min Act: -0.1700
Data Index: 8397231 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.9298. Min Act: -0.1700
Data Index: 7399884 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.9140. Min Act: -0.1700
Data Index: 4294585 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.8822. Min Act: -0.1700
Data Index: 376623 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.9140. Min Act: -0.1700
Data Index: 8722917 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.8981. Min Act: -0.1700
Data Index: 1771098 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.8664. Min Act: -0.1700
Data Index: 4480797 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.8664. Min Act: -0.1700
Data Index: 4155490 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.8505. Min Act: -0.1700
Data Index: 6559381 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1508. Min Range: -3.1508
Max Act: 2.8346. Min Act: -0.1700
Data Index: 2813210 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19