Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3328 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.7973. Min Act: -0.1700
Data Index: 5903708 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.6098. Min Act: -0.1700
Data Index: 3150816 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.5786. Min Act: -0.1700
Data Index: 6986777 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.4223. Min Act: -0.1700
Data Index: 3630813 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.3598. Min Act: -0.1700
Data Index: 5380281 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.3598. Min Act: -0.1700
Data Index: 2085034 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.3286. Min Act: -0.1700
Data Index: 2407749 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.2973. Min Act: -0.1700
Data Index: 2905447 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.2973. Min Act: -0.1700
Data Index: 8009827 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.2661. Min Act: -0.1700
Data Index: 3832757 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.2661. Min Act: -0.1700
Data Index: 5618126 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.2036. Min Act: -0.1700
Data Index: 2195140 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.1723. Min Act: -0.1700
Data Index: 511827 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.1723. Min Act: -0.1700
Data Index: 656492 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.1723. Min Act: -0.1700
Data Index: 6578814 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.1411. Min Act: -0.1700
Data Index: 2887840 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.1723. Min Act: -0.1700
Data Index: 2706090 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.1098. Min Act: -0.1700
Data Index: 7174799 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.1098. Min Act: -0.1700
Data Index: 6518155 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7973. Min Range: -7.7973
Max Act: 7.1098. Min Act: -0.1700
Data Index: 4668988 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19