Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2723. Min Range: -6.2723
Max Act: 6.2723. Min Act: -0.1700
Data Index: 2530757 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2723. Min Range: -6.2723
Max Act: 6.0223. Min Act: -0.1700
Data Index: 4647587 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2723. Min Range: -6.2723
Max Act: 6.0223. Min Act: -0.1700
Data Index: 917504 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2723. Min Range: -6.2723
Max Act: 6.0223. Min Act: -0.1700
Data Index: 7291782 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.9910. Min Act: -0.1700
Data Index: 2175320 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.9598. Min Act: -0.1700
Data Index: 2803309 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.9285. Min Act: -0.1700
Data Index: 786939 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.8973. Min Act: -0.1700
Data Index: 1066090 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.8973. Min Act: -0.1700
Data Index: 2695587 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.8348. Min Act: -0.1700
Data Index: 2193988 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.8348. Min Act: -0.1700
Data Index: 4363011 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.8348. Min Act: -0.1700
Data Index: 1949141 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.8035. Min Act: -0.1700
Data Index: 8744903 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.7723. Min Act: -0.1700
Data Index: 7943355 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.7723. Min Act: -0.1700
Data Index: 3619143 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.7410. Min Act: -0.1700
Data Index: 5523725 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.7723. Min Act: -0.1700
Data Index: 673301 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.7723. Min Act: -0.1700
Data Index: 7918391 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.7410. Min Act: -0.1700
Data Index: 106816 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2723. Min Range: -6.2723
Max Act: 5.7410. Min Act: -0.1700
Data Index: 7701226 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19