Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1625. Min Range: -7.1625
Max Act: 7.1625. Min Act: -0.1700
Data Index: 3375657 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7563. Min Act: -0.1700
Data Index: 1386526 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7250. Min Act: -0.1700
Data Index: 6647934 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7250. Min Act: -0.1700
Data Index: 1269655 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.7250. Min Act: -0.1700
Data Index: 2587955 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.6625. Min Act: -0.1700
Data Index: 139746 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.6313. Min Act: -0.1700
Data Index: 1533307 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.6313. Min Act: -0.1700
Data Index: 2434287 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.6000. Min Act: -0.1700
Data Index: 6043072 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5688. Min Act: -0.1700
Data Index: 7135753 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5375. Min Act: -0.1700
Data Index: 6304256 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5375. Min Act: -0.1700
Data Index: 1755718 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5063. Min Act: -0.1700
Data Index: 4824687 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.5063. Min Act: -0.1700
Data Index: 3032513 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.4750. Min Act: -0.1700
Data Index: 8222570 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.4750. Min Act: -0.1700
Data Index: 5493711 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.4438. Min Act: -0.1700
Data Index: 8650951 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.4438. Min Act: -0.1700
Data Index: 5170445 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.4438. Min Act: -0.1700
Data Index: 3343072 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1625. Min Range: -7.1625
Max Act: 6.4125. Min Act: -0.1700
Data Index: 4325031 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19