Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.3025. Min Act: -0.1700
Data Index: 7004188 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.3025. Min Act: -0.1700
Data Index: 5507402 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.2087. Min Act: -0.1700
Data Index: 3604042 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.2400. Min Act: -0.1700
Data Index: 5082678 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.2087. Min Act: -0.1700
Data Index: 6320814 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.1775. Min Act: -0.1700
Data Index: 4531170 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.1462. Min Act: -0.1700
Data Index: 4326803 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.0837. Min Act: -0.1700
Data Index: 815414 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.1150. Min Act: -0.1700
Data Index: 5829122 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.1150. Min Act: -0.1700
Data Index: 4562426 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.0525. Min Act: -0.1700
Data Index: 271728 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.0525. Min Act: -0.1700
Data Index: 2179987 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.0525. Min Act: -0.1700
Data Index: 7416147 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.0525. Min Act: -0.1700
Data Index: 3582622 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.0525. Min Act: -0.1700
Data Index: 6117564 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.0212. Min Act: -0.1700
Data Index: 5943144 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.0212. Min Act: -0.1700
Data Index: 1093324 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3025. Min Range: -5.3025
Max Act: 5.0212. Min Act: -0.1700
Data Index: 4251527 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3025. Min Range: -5.3025
Max Act: 4.9900. Min Act: -0.1700
Data Index: 1109570 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3025. Min Range: -5.3025
Max Act: 4.9900. Min Act: -0.1700
Data Index: 1837062 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19