Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5139 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.1220. Min Act: -0.1700
Data Index: 31806 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.1062. Min Act: -0.1700
Data Index: 5174064 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.1062. Min Act: -0.1700
Data Index: 6838186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.1062. Min Act: -0.1700
Data Index: 8413931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.1062. Min Act: -0.1700
Data Index: 1793196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0904. Min Act: -0.1700
Data Index: 7600590 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0904. Min Act: -0.1700
Data Index: 6491374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0747. Min Act: -0.1700
Data Index: 1157868 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0747. Min Act: -0.1700
Data Index: 6186246 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0589. Min Act: -0.1700
Data Index: 5339985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0589. Min Act: -0.1700
Data Index: 6819190 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0589. Min Act: -0.1700
Data Index: 3524781 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0589. Min Act: -0.1700
Data Index: 4632223 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0431. Min Act: -0.1700
Data Index: 7640720 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0431. Min Act: -0.1700
Data Index: 4434461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0431. Min Act: -0.1700
Data Index: 4492599 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0431. Min Act: -0.1700
Data Index: 1874752 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0273. Min Act: -0.1700
Data Index: 6575820 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0273. Min Act: -0.1700
Data Index: 6610208 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1220. Min Range: -3.1220
Max Act: 3.0273. Min Act: -0.1700
Data Index: 7107693 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19