Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3831 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.7049. Min Act: -0.1700
Data Index: 7704270 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6424. Min Act: -0.1700
Data Index: 5209586 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.7049. Min Act: -0.1700
Data Index: 2812980 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6424. Min Act: -0.1700
Data Index: 928106 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6424. Min Act: -0.1700
Data Index: 4376668 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6424. Min Act: -0.1700
Data Index: 3957507 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6111. Min Act: -0.1700
Data Index: 4170791 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6424. Min Act: -0.1700
Data Index: 1390311 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6111. Min Act: -0.1700
Data Index: 2818774 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6111. Min Act: -0.1700
Data Index: 1240275 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6111. Min Act: -0.1700
Data Index: 928107 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6111. Min Act: -0.1700
Data Index: 8209886 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.5486. Min Act: -0.1700
Data Index: 6390195 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.6111. Min Act: -0.1700
Data Index: 5790600 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.5799. Min Act: -0.1700
Data Index: 1466380 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.5799. Min Act: -0.1700
Data Index: 6513074 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.5799. Min Act: -0.1700
Data Index: 4535076 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.5799. Min Act: -0.1700
Data Index: 4606291 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.5799. Min Act: -0.1700
Data Index: 3190190 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7049. Min Range: -5.7049
Max Act: 5.5799. Min Act: -0.1700
Data Index: 6645199 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19