Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5676 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1887. Min Range: -6.1887
Max Act: 6.1887. Min Act: -0.1700
Data Index: 6073264 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.9699. Min Act: -0.1700
Data Index: 5506033 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.8762. Min Act: -0.1700
Data Index: 2027268 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.7824. Min Act: -0.1700
Data Index: 3709164 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.7824. Min Act: -0.1700
Data Index: 5228901 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.7199. Min Act: -0.1700
Data Index: 6701780 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.6887. Min Act: -0.1700
Data Index: 3900179 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.7199. Min Act: -0.1700
Data Index: 975976 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.6887. Min Act: -0.1700
Data Index: 2219644 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.6574. Min Act: -0.1700
Data Index: 6073266 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.6574. Min Act: -0.1700
Data Index: 5506035 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.6262. Min Act: -0.1700
Data Index: 7619312 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.6262. Min Act: -0.1700
Data Index: 6142613 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.6262. Min Act: -0.1700
Data Index: 8683562 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.6262. Min Act: -0.1700
Data Index: 7619313 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.6574. Min Act: -0.1700
Data Index: 4017956 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.5949. Min Act: -0.1700
Data Index: 6285949 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.5949. Min Act: -0.1700
Data Index: 7048205 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.5949. Min Act: -0.1700
Data Index: 2044118 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1887. Min Range: -6.1887
Max Act: 5.5949. Min Act: -0.1700
Data Index: 5228900 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19