Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5164 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.9798. Min Act: -0.1700
Data Index: 3398361 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.9798. Min Act: -0.1700
Data Index: 6365586 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.9485. Min Act: -0.1700
Data Index: 4473095 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.8860. Min Act: -0.1700
Data Index: 7190653 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.8548. Min Act: -0.1700
Data Index: 4437117 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.8235. Min Act: -0.1700
Data Index: 5355843 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.7923. Min Act: -0.1700
Data Index: 8259194 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.7610. Min Act: -0.1700
Data Index: 6517674 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.7610. Min Act: -0.1700
Data Index: 4246065 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.7923. Min Act: -0.1700
Data Index: 884099 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.7923. Min Act: -0.1700
Data Index: 3085991 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.7298. Min Act: -0.1700
Data Index: 2980145 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.7298. Min Act: -0.1700
Data Index: 1338401 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.7298. Min Act: -0.1700
Data Index: 7143691 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.7298. Min Act: -0.1700
Data Index: 8467154 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.6985. Min Act: -0.1700
Data Index: 4274492 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.6985. Min Act: -0.1700
Data Index: 1494966 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.6985. Min Act: -0.1700
Data Index: 1367183 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.6673. Min Act: -0.1700
Data Index: 2850950 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9798. Min Range: -5.9798
Max Act: 5.6985. Min Act: -0.1700
Data Index: 2643996 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19