Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.8889. Min Act: -0.1700
Data Index: 1753610 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.6389. Min Act: -0.1700
Data Index: 5237389 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.6389. Min Act: -0.1700
Data Index: 1753609 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.6077. Min Act: -0.1694
Data Index: 6288570 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.6077. Min Act: -0.1700
Data Index: 2315055 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.6077. Min Act: -0.1700
Data Index: 6084700 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.6077. Min Act: -0.1700
Data Index: 7762572 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5764. Min Act: -0.1700
Data Index: 2145458 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5764. Min Act: -0.1699
Data Index: 6900658 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5764. Min Act: -0.1700
Data Index: 2742245 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5764. Min Act: -0.1700
Data Index: 8589165 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5764. Min Act: -0.1700
Data Index: 2971912 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5139. Min Act: -0.1700
Data Index: 1919750 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5452. Min Act: -0.1700
Data Index: 3909696 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5139. Min Act: -0.1700
Data Index: 7303025 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5139. Min Act: -0.1700
Data Index: 3651398 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.5139. Min Act: -0.1700
Data Index: 6303541 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.4827. Min Act: -0.1700
Data Index: 7248586 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.4827. Min Act: -0.1700
Data Index: 1087317 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8889. Min Range: -5.8889
Max Act: 5.4827. Min Act: -0.1700
Data Index: 1103105 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19