Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 707 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.7412. Min Act: -0.1700
Data Index: 7383380 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.6162. Min Act: -0.1700
Data Index: 8533142 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.3662. Min Act: -0.1700
Data Index: 6273084 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.3662. Min Act: -0.1700
Data Index: 8537363 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.3975. Min Act: -0.1700
Data Index: 4634748 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.3350. Min Act: -0.1700
Data Index: 2726264 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.3037. Min Act: -0.1700
Data Index: 36815 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.2725. Min Act: -0.1700
Data Index: 3302580 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.2412. Min Act: -0.1700
Data Index: 495362 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.2412. Min Act: -0.1700
Data Index: 3991621 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.1787. Min Act: -0.1700
Data Index: 7546888 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.1475. Min Act: -0.1700
Data Index: 2243828 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.1787. Min Act: -0.1700
Data Index: 2200026 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.1475. Min Act: -0.1700
Data Index: 1636044 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.1162. Min Act: -0.1700
Data Index: 8807793 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.1162. Min Act: -0.1700
Data Index: 7798793 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.1162. Min Act: -0.1700
Data Index: 36818 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.0850. Min Act: -0.1700
Data Index: 1029994 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.0850. Min Act: -0.1700
Data Index: 5488077 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7412. Min Range: -5.7412
Max Act: 5.0537. Min Act: -0.1700
Data Index: 6492480 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19