Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1723. Min Range: -6.1723
Max Act: 6.1723. Min Act: -0.1700
Data Index: 1324286 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.9848. Min Act: -0.1700
Data Index: 3729927 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.9223. Min Act: -0.1700
Data Index: 475109 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.7973. Min Act: -0.1700
Data Index: 78247 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.6723. Min Act: -0.1700
Data Index: 6194793 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.7036. Min Act: -0.1700
Data Index: 121388 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.7036. Min Act: -0.1700
Data Index: 286014 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.6411. Min Act: -0.1700
Data Index: 8143862 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.6411. Min Act: -0.1700
Data Index: 1615110 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.6723. Min Act: -0.1700
Data Index: 2935413 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.6411. Min Act: -0.1700
Data Index: 3372918 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.6098. Min Act: -0.1700
Data Index: 7423304 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.6098. Min Act: -0.1700
Data Index: 5357773 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.6098. Min Act: -0.1700
Data Index: 4988226 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.5786. Min Act: -0.1700
Data Index: 3107844 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.5786. Min Act: -0.1700
Data Index: 685101 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.5473. Min Act: -0.1700
Data Index: 8302576 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.5473. Min Act: -0.1700
Data Index: 1960442 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.5473. Min Act: -0.1700
Data Index: 5476735 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1723. Min Range: -6.1723
Max Act: 5.5161. Min Act: -0.1700
Data Index: 5909169 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19