Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3097 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.2767. Min Act: -0.1700
Data Index: 7403168 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.2767. Min Act: -0.1700
Data Index: 5431997 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.2454. Min Act: -0.1700
Data Index: 6381025 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.2142. Min Act: -0.1700
Data Index: 6216821 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.2142. Min Act: -0.1700
Data Index: 2212925 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.2142. Min Act: -0.1700
Data Index: 6959965 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.1829. Min Act: -0.1700
Data Index: 7306020 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.1517. Min Act: -0.1700
Data Index: 6086352 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.1517. Min Act: -0.1700
Data Index: 4583456 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.1204. Min Act: -0.1700
Data Index: 6191673 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.1204. Min Act: -0.1700
Data Index: 6290662 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.1204. Min Act: -0.1700
Data Index: 2849428 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.0579. Min Act: -0.1700
Data Index: 223919 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.0892. Min Act: -0.1700
Data Index: 6298009 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.0579. Min Act: -0.1700
Data Index: 6862932 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.0579. Min Act: -0.1700
Data Index: 8718239 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.0267. Min Act: -0.1700
Data Index: 2240320 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.0267. Min Act: -0.1700
Data Index: 4471785 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.0267. Min Act: -0.1700
Data Index: 2918283 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2767. Min Range: -5.2767
Max Act: 5.0267. Min Act: -0.1700
Data Index: 7991003 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19