Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1157. Min Range: -7.1157
Max Act: 7.1157. Min Act: -0.1700
Data Index: 1148278 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1157. Min Range: -7.1157
Max Act: 7.0219. Min Act: -0.1700
Data Index: 1861459 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1157. Min Range: -7.1157
Max Act: 7.0219. Min Act: -0.1700
Data Index: 4787923 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.8657. Min Act: -0.1700
Data Index: 8523836 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.8657. Min Act: -0.1700
Data Index: 7954096 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.8344. Min Act: -0.1700
Data Index: 7917267 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.8344. Min Act: -0.1700
Data Index: 6440616 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.7719. Min Act: -0.1700
Data Index: 4907869 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.8344. Min Act: -0.1700
Data Index: 7718270 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.7719. Min Act: -0.1700
Data Index: 504691 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.7719. Min Act: -0.1700
Data Index: 812950 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.6782. Min Act: -0.1700
Data Index: 1691656 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.7094. Min Act: -0.1700
Data Index: 8081062 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.7094. Min Act: -0.1700
Data Index: 7999760 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.6782. Min Act: -0.1700
Data Index: 2657860 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.6782. Min Act: -0.1700
Data Index: 8263730 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.6469. Min Act: -0.1700
Data Index: 5859723 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.6782. Min Act: -0.1700
Data Index: 104653 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.6469. Min Act: -0.1700
Data Index: 2924149 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1157. Min Range: -7.1157
Max Act: 6.6782. Min Act: -0.1700
Data Index: 617040 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19