Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1246 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1723. Min Range: -7.1723
Max Act: 7.1723. Min Act: -0.1700
Data Index: 1506901 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1723. Min Range: -7.1723
Max Act: 7.1098. Min Act: -0.1700
Data Index: 8021506 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1723. Min Range: -7.1723
Max Act: 7.0473. Min Act: -0.1700
Data Index: 58238 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.9535. Min Act: -0.1700
Data Index: 7703294 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.9535. Min Act: -0.1700
Data Index: 3502729 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.9223. Min Act: -0.1700
Data Index: 4542170 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.8285. Min Act: -0.1700
Data Index: 4352335 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.8285. Min Act: -0.1700
Data Index: 4350359 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.8285. Min Act: -0.1700
Data Index: 5220353 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.8285. Min Act: -0.1700
Data Index: 6436737 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.7660. Min Act: -0.1700
Data Index: 7363779 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.7660. Min Act: -0.1700
Data Index: 4737295 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.7660. Min Act: -0.1700
Data Index: 6424675 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.7035. Min Act: -0.1700
Data Index: 8118668 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.7035. Min Act: -0.1700
Data Index: 5274036 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.7035. Min Act: -0.1700
Data Index: 4878823 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.6410. Min Act: -0.1700
Data Index: 3144526 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.6723. Min Act: -0.1700
Data Index: 8824306 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.6723. Min Act: -0.1700
Data Index: 6812231 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1723. Min Range: -7.1723
Max Act: 6.6410. Min Act: -0.1700
Data Index: 2997583 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19