Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4346 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.4715. Min Act: -0.1700
Data Index: 639458 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.3153. Min Act: -0.1700
Data Index: 5128064 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.2215. Min Act: -0.1700
Data Index: 1318842 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.1903. Min Act: -0.1700
Data Index: 2994262 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.1590. Min Act: -0.1700
Data Index: 2019609 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.1903. Min Act: -0.1700
Data Index: 5139134 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.1278. Min Act: -0.1700
Data Index: 2157107 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.1278. Min Act: -0.1700
Data Index: 584154 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.0965. Min Act: -0.1700
Data Index: 4597942 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.1278. Min Act: -0.1700
Data Index: 781988 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.0653. Min Act: -0.1700
Data Index: 1044565 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.0965. Min Act: -0.1700
Data Index: 1266794 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.0340. Min Act: -0.1700
Data Index: 1943281 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.0028. Min Act: -0.1700
Data Index: 1452153 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.0028. Min Act: -0.1700
Data Index: 5455597 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.0340. Min Act: -0.1700
Data Index: 449072 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4715. Min Range: -7.4715
Max Act: 7.0028. Min Act: -0.1700
Data Index: 831219 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4715. Min Range: -7.4715
Max Act: 6.9403. Min Act: -0.1700
Data Index: 4894103 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4715. Min Range: -7.4715
Max Act: 6.9090. Min Act: -0.1700
Data Index: 8561388 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4715. Min Range: -7.4715
Max Act: 6.9715. Min Act: -0.1700
Data Index: 3133543 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19