Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0199. Min Range: -7.0199
Max Act: 7.0199. Min Act: -0.1700
Data Index: 7846932 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.8324. Min Act: -0.1700
Data Index: 2191136 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.8011. Min Act: -0.1700
Data Index: 6526820 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.8011. Min Act: -0.1700
Data Index: 5267904 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.7386. Min Act: -0.1700
Data Index: 6952015 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.7074. Min Act: -0.1700
Data Index: 455434 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.7074. Min Act: -0.1700
Data Index: 6893267 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.6136. Min Act: -0.1700
Data Index: 7541729 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.6136. Min Act: -0.1700
Data Index: 3916792 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.6136. Min Act: -0.1700
Data Index: 771217 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.5511. Min Act: -0.1700
Data Index: 6751295 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.5511. Min Act: -0.1700
Data Index: 3579790 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.5824. Min Act: -0.1700
Data Index: 6932978 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.5199. Min Act: -0.1700
Data Index: 6917173 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4886. Min Act: -0.1700
Data Index: 4485696 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4574. Min Act: -0.1700
Data Index: 7482556 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4574. Min Act: -0.1700
Data Index: 7322139 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4574. Min Act: -0.1700
Data Index: 5086898 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.4574. Min Act: -0.1700
Data Index: 6858086 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0199. Min Range: -7.0199
Max Act: 6.3949. Min Act: -0.1700
Data Index: 2137723 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19