Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1563 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1808. Min Range: -8.1808
Max Act: 8.1808. Min Act: -0.1700
Data Index: 3508637 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1808. Min Range: -8.1808
Max Act: 8.1183. Min Act: -0.1700
Data Index: 7075413 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.9308. Min Act: -0.1700
Data Index: 5353274 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.9933. Min Act: -0.1700
Data Index: 6100974 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.8995. Min Act: -0.1700
Data Index: 2161573 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.8370. Min Act: -0.1700
Data Index: 2419096 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.8370. Min Act: -0.1700
Data Index: 3241620 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.8370. Min Act: -0.1700
Data Index: 3974664 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.8370. Min Act: -0.1700
Data Index: 8360897 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.8370. Min Act: -0.1700
Data Index: 4247330 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.7745. Min Act: -0.1700
Data Index: 2285775 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.8058. Min Act: -0.1700
Data Index: 901214 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.8058. Min Act: -0.1700
Data Index: 2447988 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.7745. Min Act: -0.1700
Data Index: 853861 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.7745. Min Act: -0.1700
Data Index: 4236209 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.7745. Min Act: -0.1700
Data Index: 3704025 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.7433. Min Act: -0.1700
Data Index: 7852209 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.7433. Min Act: -0.1700
Data Index: 2658277 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.7433. Min Act: -0.1700
Data Index: 2427509 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1808. Min Range: -8.1808
Max Act: 7.7433. Min Act: -0.1700
Data Index: 4124659 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19