Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4347 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.3126. Min Act: -0.1700
Data Index: 4327548 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.2814. Min Act: -0.1700
Data Index: 2280296 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.1564. Min Act: -0.1700
Data Index: 3779304 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.0939. Min Act: -0.1700
Data Index: 7823489 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.0626. Min Act: -0.1700
Data Index: 125579 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.0313. Min Act: -0.1700
Data Index: 7472120 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.0313. Min Act: -0.1700
Data Index: 8573682 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.0313. Min Act: -0.1700
Data Index: 8739743 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.0001. Min Act: -0.1700
Data Index: 5611110 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.0001. Min Act: -0.1700
Data Index: 4403697 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3126. Min Range: -4.3126
Max Act: 4.0001. Min Act: -0.1700
Data Index: 2717128 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3126. Min Range: -4.3126
Max Act: 3.9376. Min Act: -0.1700
Data Index: 5032627 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3126. Min Range: -4.3126
Max Act: 3.9376. Min Act: -0.1700
Data Index: 3324519 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3126. Min Range: -4.3126
Max Act: 3.9688. Min Act: -0.1700
Data Index: 1914218 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3126. Min Range: -4.3126
Max Act: 3.9376. Min Act: -0.1700
Data Index: 262138 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3126. Min Range: -4.3126
Max Act: 3.9376. Min Act: -0.1700
Data Index: 1613819 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3126. Min Range: -4.3126
Max Act: 3.9376. Min Act: -0.1700
Data Index: 7566638 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3126. Min Range: -4.3126
Max Act: 3.9376. Min Act: -0.1700
Data Index: 8596567 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3126. Min Range: -4.3126
Max Act: 3.9376. Min Act: -0.1700
Data Index: 8509315 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3126. Min Range: -4.3126
Max Act: 3.9063. Min Act: -0.1700
Data Index: 7340970 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19