Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0736. Min Range: -7.0736
Max Act: 7.0736. Min Act: -0.1700
Data Index: 5807487 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.8236. Min Act: -0.1700
Data Index: 1927139 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.7298. Min Act: -0.1700
Data Index: 4405527 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.7298. Min Act: -0.1700
Data Index: 2965696 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.6673. Min Act: -0.1700
Data Index: 2137302 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.6361. Min Act: -0.1700
Data Index: 8680193 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.6048. Min Act: -0.1700
Data Index: 535369 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.5736. Min Act: -0.1700
Data Index: 4478010 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.5423. Min Act: -0.1700
Data Index: 6091178 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.5423. Min Act: -0.1700
Data Index: 1127143 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.5423. Min Act: -0.1700
Data Index: 5013103 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.5423. Min Act: -0.1700
Data Index: 2881825 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.5111. Min Act: -0.1700
Data Index: 4823846 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.4798. Min Act: -0.1700
Data Index: 891279 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.4798. Min Act: -0.1700
Data Index: 3633642 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.5111. Min Act: -0.1700
Data Index: 3379369 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.4486. Min Act: -0.1700
Data Index: 88808 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.4173. Min Act: -0.1700
Data Index: 2693008 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.4486. Min Act: -0.1700
Data Index: 366793 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0736. Min Range: -7.0736
Max Act: 6.4798. Min Act: -0.1700
Data Index: 8069367 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19