Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0012. Min Range: -4.0012
Max Act: 4.0012. Min Act: -0.1700
Data Index: 4223966 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.9699. Min Act: -0.1700
Data Index: 8246769 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.9387. Min Act: -0.1700
Data Index: 279991 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.9074. Min Act: -0.1700
Data Index: 3565989 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.9699. Min Act: -0.1700
Data Index: 4858770 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.9074. Min Act: -0.1700
Data Index: 3047285 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8761. Min Act: -0.1700
Data Index: 5655295 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8761. Min Act: -0.1700
Data Index: 4483347 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8761. Min Act: -0.1700
Data Index: 5009100 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8761. Min Act: -0.1700
Data Index: 7686370 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8136. Min Act: -0.1700
Data Index: 3565986 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8449. Min Act: -0.1700
Data Index: 573260 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8449. Min Act: -0.1700
Data Index: 7017560 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8136. Min Act: -0.1700
Data Index: 6677682 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8136. Min Act: -0.1700
Data Index: 7527150 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8136. Min Act: -0.1700
Data Index: 4788100 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8136. Min Act: -0.1700
Data Index: 6449009 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.8136. Min Act: -0.1700
Data Index: 4561188 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.7823. Min Act: -0.1700
Data Index: 3565982 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0012. Min Range: -4.0012
Max Act: 3.7511. Min Act: -0.1700
Data Index: 914801 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19