Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0793. Min Range: -6.0793
Max Act: 6.0793. Min Act: -0.1700
Data Index: 3268760 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.8918. Min Act: -0.1700
Data Index: 8670310 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.8606. Min Act: -0.1700
Data Index: 733250 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.8606. Min Act: -0.1700
Data Index: 2942685 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.8606. Min Act: -0.1700
Data Index: 2733645 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.7668. Min Act: -0.1700
Data Index: 7224931 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.7668. Min Act: -0.1700
Data Index: 6538787 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.7356. Min Act: -0.1700
Data Index: 4081028 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.6731. Min Act: -0.1700
Data Index: 692656 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.6731. Min Act: -0.1700
Data Index: 5127021 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.6731. Min Act: -0.1700
Data Index: 8790275 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.6418. Min Act: -0.1700
Data Index: 7649768 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.6418. Min Act: -0.1700
Data Index: 6952291 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.6418. Min Act: -0.1700
Data Index: 1049197 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.5793. Min Act: -0.1700
Data Index: 326275 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.5793. Min Act: -0.1700
Data Index: 4260548 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.5793. Min Act: -0.1700
Data Index: 121546 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.5793. Min Act: -0.1700
Data Index: 8059304 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.5793. Min Act: -0.1700
Data Index: 4830564 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0793. Min Range: -6.0793
Max Act: 5.5481. Min Act: -0.1700
Data Index: 3713260 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19