Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0156. Min Range: -5.0156
Max Act: 5.0156. Min Act: -0.1700
Data Index: 3593440 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.7031. Min Act: -0.1700
Data Index: 4731419 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.6719. Min Act: -0.1700
Data Index: 8190359 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.6406. Min Act: -0.1700
Data Index: 1742539 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.6406. Min Act: -0.1700
Data Index: 3787110 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.6406. Min Act: -0.1700
Data Index: 5624279 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.6094. Min Act: -0.1700
Data Index: 7950621 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.6094. Min Act: -0.1700
Data Index: 6045102 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5781. Min Act: -0.1700
Data Index: 6045101 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5781. Min Act: -0.1700
Data Index: 4650614 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.6094. Min Act: -0.1700
Data Index: 6045099 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5781. Min Act: -0.1700
Data Index: 6788428 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5781. Min Act: -0.1700
Data Index: 540190 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5781. Min Act: -0.1700
Data Index: 7718304 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5469. Min Act: -0.1700
Data Index: 3863159 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5469. Min Act: -0.1700
Data Index: 3484940 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5781. Min Act: -0.1700
Data Index: 7249273 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5781. Min Act: -0.1700
Data Index: 7075828 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5156. Min Act: -0.1700
Data Index: 5857467 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0156. Min Range: -5.0156
Max Act: 4.5156. Min Act: -0.1700
Data Index: 4588806 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19