Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.8807. Min Act: -0.1700
Data Index: 1996011 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.6620. Min Act: -0.1700
Data Index: 6242414 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.6307. Min Act: -0.1700
Data Index: 2703820 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.6307. Min Act: -0.1700
Data Index: 42483 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.5995. Min Act: -0.1700
Data Index: 406360 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.5995. Min Act: -0.1700
Data Index: 5039573 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.5995. Min Act: -0.1700
Data Index: 4604498 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.5995. Min Act: -0.1700
Data Index: 5702504 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.5057. Min Act: -0.1700
Data Index: 3743815 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.4432. Min Act: -0.1700
Data Index: 3149886 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.4120. Min Act: -0.1700
Data Index: 6010668 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.4120. Min Act: -0.1700
Data Index: 287156 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.3807. Min Act: -0.1700
Data Index: 1605903 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.3495. Min Act: -0.1700
Data Index: 2711342 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.3807. Min Act: -0.1700
Data Index: 7045455 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.3182. Min Act: -0.1700
Data Index: 3183862 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.3807. Min Act: -0.1700
Data Index: 7243877 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.3495. Min Act: -0.1700
Data Index: 5829660 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.3495. Min Act: -0.1700
Data Index: 4487814 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8807. Min Range: -6.8807
Max Act: 6.3182. Min Act: -0.1700
Data Index: 1664960 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19