Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.8746. Min Act: -0.1700
Data Index: 3760224 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.5621. Min Act: -0.1700
Data Index: 3591854 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.5621. Min Act: -0.1700
Data Index: 6646752 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.5309. Min Act: -0.1700
Data Index: 471279 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.4996. Min Act: -0.1700
Data Index: 4945175 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.4371. Min Act: -0.1700
Data Index: 8609071 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.4059. Min Act: -0.1700
Data Index: 7810666 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.4059. Min Act: -0.1700
Data Index: 675621 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.3434. Min Act: -0.1700
Data Index: 7634565 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.3121. Min Act: -0.1700
Data Index: 7755587 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.3121. Min Act: -0.1700
Data Index: 2563781 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.2184. Min Act: -0.1700
Data Index: 8375398 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.2184. Min Act: -0.1700
Data Index: 755292 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.2184. Min Act: -0.1700
Data Index: 3091781 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.1871. Min Act: -0.1700
Data Index: 5903446 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.0934. Min Act: -0.1700
Data Index: 5935744 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.0934. Min Act: -0.1700
Data Index: 6152024 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.0934. Min Act: -0.1700
Data Index: 5255244 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.0621. Min Act: -0.1700
Data Index: 8754624 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8746. Min Range: -7.8746
Max Act: 7.0309. Min Act: -0.1700
Data Index: 1682547 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19