Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.3934. Min Act: -0.1700
Data Index: 371925 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.3622. Min Act: -0.1700
Data Index: 5927301 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.2684. Min Act: -0.1700
Data Index: 3063587 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.2684. Min Act: -0.1700
Data Index: 5177592 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.2684. Min Act: -0.1700
Data Index: 4362504 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.2372. Min Act: -0.1700
Data Index: 8514821 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.2372. Min Act: -0.1700
Data Index: 4593449 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.2372. Min Act: -0.1700
Data Index: 2271655 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.2059. Min Act: -0.1700
Data Index: 4587751 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.2059. Min Act: -0.1700
Data Index: 4319494 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.1747. Min Act: -0.1700
Data Index: 8460896 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.1747. Min Act: -0.1700
Data Index: 1593847 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.1747. Min Act: -0.1700
Data Index: 773746 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.1747. Min Act: -0.1700
Data Index: 3344615 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.1747. Min Act: -0.1700
Data Index: 1109893 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.1747. Min Act: -0.1700
Data Index: 422799 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.2059. Min Act: -0.1700
Data Index: 1763412 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.1434. Min Act: -0.1700
Data Index: 4120855 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.1434. Min Act: -0.1700
Data Index: 4930854 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3934. Min Range: -5.3934
Max Act: 5.1434. Min Act: -0.1700
Data Index: 4873845 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19