Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2507 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0587. Min Range: -5.0587
Max Act: 5.0587. Min Act: -0.1700
Data Index: 1137826 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0587. Min Range: -5.0587
Max Act: 5.0587. Min Act: -0.1700
Data Index: 6855449 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0587. Min Range: -5.0587
Max Act: 5.0275. Min Act: -0.1700
Data Index: 4936990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.8712. Min Act: -0.1700
Data Index: 5714177 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.8400. Min Act: -0.1700
Data Index: 6737505 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.8712. Min Act: -0.1700
Data Index: 8566435 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.8087. Min Act: -0.1700
Data Index: 8699847 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.8087. Min Act: -0.1700
Data Index: 1773562 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.7462. Min Act: -0.1700
Data Index: 2199858 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.7775. Min Act: -0.1700
Data Index: 7513996 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.7775. Min Act: -0.1700
Data Index: 657467 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.7775. Min Act: -0.1700
Data Index: 6481676 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.7462. Min Act: -0.1700
Data Index: 1521554 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.7462. Min Act: -0.1700
Data Index: 7650817 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.7462. Min Act: -0.1700
Data Index: 2292818 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.6837. Min Act: -0.1700
Data Index: 2117666 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.7150. Min Act: -0.1700
Data Index: 4323684 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.7150. Min Act: -0.1700
Data Index: 1454531 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.6837. Min Act: -0.1700
Data Index: 1809520 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0587. Min Range: -5.0587
Max Act: 4.6837. Min Act: -0.1700
Data Index: 2220561 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19