Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1559 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4404. Min Range: -6.4404
Max Act: 6.4404. Min Act: -0.1700
Data Index: 5639532 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4404. Min Range: -6.4404
Max Act: 6.1279. Min Act: -0.1700
Data Index: 2750772 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4404. Min Range: -6.4404
Max Act: 6.0654. Min Act: -0.1700
Data Index: 4723520 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4404. Min Range: -6.4404
Max Act: 6.0029. Min Act: -0.1700
Data Index: 8146466 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.9404. Min Act: -0.1700
Data Index: 5987095 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.8779. Min Act: -0.1700
Data Index: 2560384 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.8154. Min Act: -0.1700
Data Index: 3317197 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.8154. Min Act: -0.1700
Data Index: 1423109 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.8466. Min Act: -0.1700
Data Index: 7659575 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.7841. Min Act: -0.1700
Data Index: 8588043 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.8154. Min Act: -0.1700
Data Index: 2772799 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.8154. Min Act: -0.1700
Data Index: 3444679 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.8154. Min Act: -0.1700
Data Index: 1515301 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.7841. Min Act: -0.1700
Data Index: 1268854 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.7529. Min Act: -0.1700
Data Index: 3954323 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.7529. Min Act: -0.1700
Data Index: 7876408 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.7529. Min Act: -0.1700
Data Index: 7962592 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.7216. Min Act: -0.1700
Data Index: 3185486 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.7216. Min Act: -0.1700
Data Index: 6344042 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4404. Min Range: -6.4404
Max Act: 5.6904. Min Act: -0.1700
Data Index: 3006066 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19