Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.8633. Min Act: -0.1700
Data Index: 5586691 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.8008. Min Act: -0.1700
Data Index: 2157860 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.8008. Min Act: -0.1700
Data Index: 1026012 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7383. Min Act: -0.1700
Data Index: 8078693 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7696. Min Act: -0.1700
Data Index: 4371789 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7383. Min Act: -0.1700
Data Index: 7977887 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7696. Min Act: -0.1700
Data Index: 4291510 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7383. Min Act: -0.1700
Data Index: 3847035 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7383. Min Act: -0.1700
Data Index: 4354846 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7383. Min Act: -0.1700
Data Index: 5412476 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7383. Min Act: -0.1700
Data Index: 1506836 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7071. Min Act: -0.1700
Data Index: 4996065 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7071. Min Act: -0.1700
Data Index: 2955809 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7071. Min Act: -0.1700
Data Index: 6027139 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.6758. Min Act: -0.1700
Data Index: 4189105 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3681837 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3679663 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.6758. Min Act: -0.1700
Data Index: 2201667 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.6758. Min Act: -0.1700
Data Index: 7084278 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.6758. Min Act: -0.1700
Data Index: 7348426 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19