Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2372 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1267. Min Range: -7.1267
Max Act: 7.1267. Min Act: -0.1700
Data Index: 7361419 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.9704. Min Act: -0.1700
Data Index: 6667696 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.8142. Min Act: -0.1700
Data Index: 3447857 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.7517. Min Act: -0.1700
Data Index: 3023534 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.5954. Min Act: -0.1700
Data Index: 7636612 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.5017. Min Act: -0.1700
Data Index: 8436116 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.4704. Min Act: -0.1700
Data Index: 5956775 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.4704. Min Act: -0.1700
Data Index: 7567898 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.4392. Min Act: -0.1700
Data Index: 7533616 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.4079. Min Act: -0.1700
Data Index: 4845552 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.4079. Min Act: -0.1700
Data Index: 4402959 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.4079. Min Act: -0.1700
Data Index: 7689338 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.4079. Min Act: -0.1700
Data Index: 2844148 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.3767. Min Act: -0.1700
Data Index: 6728548 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.4079. Min Act: -0.1700
Data Index: 6167414 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.4079. Min Act: -0.1700
Data Index: 1796556 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.3454. Min Act: -0.1700
Data Index: 173707 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.3767. Min Act: -0.1700
Data Index: 2947301 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.3767. Min Act: -0.1700
Data Index: 1710745 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1267. Min Range: -7.1267
Max Act: 6.3454. Min Act: -0.1700
Data Index: 866851 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19