Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4130 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1035. Min Range: -4.1035
Max Act: 4.1035. Min Act: -0.1700
Data Index: 8801513 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.9785. Min Act: -0.1700
Data Index: 2888867 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.9159. Min Act: -0.1700
Data Index: 2258259 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.8690. Min Act: -0.1700
Data Index: 4072399 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.8378. Min Act: -0.1700
Data Index: 2664999 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.8221. Min Act: -0.1700
Data Index: 6019587 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.7752. Min Act: -0.1700
Data Index: 2631563 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.7283. Min Act: -0.1700
Data Index: 4998428 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.7127. Min Act: -0.1700
Data Index: 8687296 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.7283. Min Act: -0.1700
Data Index: 8711987 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6970. Min Act: -0.1700
Data Index: 7192151 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6970. Min Act: -0.1700
Data Index: 4163484 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6501. Min Act: -0.1700
Data Index: 1991475 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6814. Min Act: -0.1700
Data Index: 6473483 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6814. Min Act: -0.1700
Data Index: 5152907 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6501. Min Act: -0.1700
Data Index: 5143389 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6501. Min Act: -0.1700
Data Index: 2813568 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6657. Min Act: -0.1700
Data Index: 7672462 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6970. Min Act: -0.1700
Data Index: 930591 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1035. Min Range: -4.1035
Max Act: 3.6188. Min Act: -0.1700
Data Index: 758637 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19