Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5431 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7095. Min Range: -6.7095
Max Act: 6.7095. Min Act: -0.1700
Data Index: 5144702 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7095. Min Range: -6.7095
Max Act: 6.4282. Min Act: -0.1700
Data Index: 378490 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7095. Min Range: -6.7095
Max Act: 6.3970. Min Act: -0.1700
Data Index: 4524373 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7095. Min Range: -6.7095
Max Act: 6.1782. Min Act: -0.1700
Data Index: 1498622 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7095. Min Range: -6.7095
Max Act: 6.1470. Min Act: -0.1700
Data Index: 974259 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7095. Min Range: -6.7095
Max Act: 6.0532. Min Act: -0.1700
Data Index: 6170529 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7095. Min Range: -6.7095
Max Act: 6.0532. Min Act: -0.1700
Data Index: 236258 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7095. Min Range: -6.7095
Max Act: 6.0220. Min Act: -0.1700
Data Index: 8639088 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9595. Min Act: -0.1700
Data Index: 8437826 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7095. Min Range: -6.7095
Max Act: 6.0220. Min Act: -0.1700
Data Index: 3854918 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9907. Min Act: -0.1700
Data Index: 5152505 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9907. Min Act: -0.1700
Data Index: 3493104 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9595. Min Act: -0.1700
Data Index: 8114557 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9282. Min Act: -0.1700
Data Index: 4179062 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9595. Min Act: -0.1700
Data Index: 5060896 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9282. Min Act: -0.1700
Data Index: 5945217 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9282. Min Act: -0.1700
Data Index: 6438988 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9282. Min Act: -0.1700
Data Index: 5759592 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.9282. Min Act: -0.1700
Data Index: 3217007 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7095. Min Range: -6.7095
Max Act: 5.8657. Min Act: -0.1700
Data Index: 8384874 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19