Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6171 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2025. Min Range: -6.2025
Max Act: 6.2025. Min Act: -0.1700
Data Index: 3257503 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2025. Min Range: -6.2025
Max Act: 6.0462. Min Act: -0.1700
Data Index: 1524990 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2025. Min Range: -6.2025
Max Act: 6.0462. Min Act: -0.1700
Data Index: 1464142 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2025. Min Range: -6.2025
Max Act: 6.0150. Min Act: -0.1700
Data Index: 3964590 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.9212. Min Act: -0.1700
Data Index: 6488813 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.9212. Min Act: -0.1700
Data Index: 6714019 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.8900. Min Act: -0.1700
Data Index: 2039863 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.8587. Min Act: -0.1700
Data Index: 7389991 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.8900. Min Act: -0.1700
Data Index: 2913863 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.8275. Min Act: -0.1700
Data Index: 5277566 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.8275. Min Act: -0.1700
Data Index: 1097714 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7962. Min Act: -0.1700
Data Index: 6916699 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7962. Min Act: -0.1700
Data Index: 8392777 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7025. Min Act: -0.1700
Data Index: 1376770 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7337. Min Act: -0.1700
Data Index: 6468038 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7337. Min Act: -0.1700
Data Index: 2314754 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7025. Min Act: -0.1700
Data Index: 7977951 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7025. Min Act: -0.1700
Data Index: 2662442 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.7025. Min Act: -0.1700
Data Index: 1961663 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2025. Min Range: -6.2025
Max Act: 5.6712. Min Act: -0.1700
Data Index: 6788005 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19