Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 84 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.7053. Min Act: -0.1700
Data Index: 8318890 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.6428. Min Act: -0.1700
Data Index: 6505331 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.6116. Min Act: -0.1700
Data Index: 7101016 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.6116. Min Act: -0.1700
Data Index: 5235656 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.6428. Min Act: -0.1700
Data Index: 8318900 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.6428. Min Act: -0.1700
Data Index: 4116194 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.6428. Min Act: -0.1700
Data Index: 8318899 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.6428. Min Act: -0.1700
Data Index: 7475410 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5803. Min Act: -0.1700
Data Index: 8318904 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5803. Min Act: -0.1700
Data Index: 8318901 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5803. Min Act: -0.1700
Data Index: 2027692 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5803. Min Act: -0.1700
Data Index: 558803 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5491. Min Act: -0.1700
Data Index: 1835220 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5803. Min Act: -0.1700
Data Index: 8318905 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5803. Min Act: -0.1700
Data Index: 5079191 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5803. Min Act: -0.1700
Data Index: 8318885 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5491. Min Act: -0.1700
Data Index: 1082048 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5178. Min Act: -0.1700
Data Index: 8318892 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5491. Min Act: -0.1700
Data Index: 8318902 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7053. Min Range: -5.7053
Max Act: 5.5178. Min Act: -0.1700
Data Index: 4521836 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19