Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 932 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.1910. Min Act: -0.1700
Data Index: 404031 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.0660. Min Act: -0.1700
Data Index: 8009801 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.0347. Min Act: -0.1700
Data Index: 5538275 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1910. Min Range: -6.1910
Max Act: 6.0035. Min Act: -0.1700
Data Index: 6932297 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.9722. Min Act: -0.1700
Data Index: 5422058 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.9722. Min Act: -0.1700
Data Index: 4902970 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8472. Min Act: -0.1700
Data Index: 4323196 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8785. Min Act: -0.1700
Data Index: 4432958 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8785. Min Act: -0.1700
Data Index: 3270148 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8785. Min Act: -0.1700
Data Index: 5662458 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8472. Min Act: -0.1700
Data Index: 331280 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8160. Min Act: -0.1700
Data Index: 2656911 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8160. Min Act: -0.1700
Data Index: 7528781 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.7847. Min Act: -0.1700
Data Index: 5973809 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8160. Min Act: -0.1700
Data Index: 8533896 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8160. Min Act: -0.1700
Data Index: 911229 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.7847. Min Act: -0.1700
Data Index: 1567513 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.8160. Min Act: -0.1700
Data Index: 8292764 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.7535. Min Act: -0.1700
Data Index: 2569242 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1910. Min Range: -6.1910
Max Act: 5.7222. Min Act: -0.1700
Data Index: 3010809 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19