Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2791 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9248. Min Range: -7.9248
Max Act: 7.9248. Min Act: -0.1700
Data Index: 1545042 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9248. Min Range: -7.9248
Max Act: 7.7686. Min Act: -0.1700
Data Index: 8070147 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9248. Min Range: -7.9248
Max Act: 7.5186. Min Act: -0.1700
Data Index: 2855231 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9248. Min Range: -7.9248
Max Act: 7.3936. Min Act: -0.1700
Data Index: 1870279 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9248. Min Range: -7.9248
Max Act: 7.2686. Min Act: -0.1700
Data Index: 481220 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9248. Min Range: -7.9248
Max Act: 7.2686. Min Act: -0.1700
Data Index: 295651 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9248. Min Range: -7.9248
Max Act: 7.1123. Min Act: -0.1700
Data Index: 3728373 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9248. Min Range: -7.9248
Max Act: 7.0498. Min Act: -0.1700
Data Index: 7788646 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9248. Min Range: -7.9248
Max Act: 7.0498. Min Act: -0.1700
Data Index: 2291593 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.9248. Min Act: -0.1700
Data Index: 5799410 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.8936. Min Act: -0.1700
Data Index: 3834902 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.8936. Min Act: -0.1700
Data Index: 3026025 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.8623. Min Act: -0.1700
Data Index: 602400 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.8311. Min Act: -0.1700
Data Index: 1303037 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.7998. Min Act: -0.1700
Data Index: 1966815 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.7998. Min Act: -0.1700
Data Index: 939144 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.7686. Min Act: -0.1700
Data Index: 3318936 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.7686. Min Act: -0.1700
Data Index: 6077653 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.7373. Min Act: -0.1700
Data Index: 723129 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9248. Min Range: -7.9248
Max Act: 6.7686. Min Act: -0.1700
Data Index: 63239 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19