Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3751 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.8104. Min Act: -0.1700
Data Index: 2172836 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7791. Min Act: -0.1700
Data Index: 607121 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7791. Min Act: -0.1700
Data Index: 5062513 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4843392 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4611594 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7479. Min Act: -0.1700
Data Index: 1450201 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7479. Min Act: -0.1700
Data Index: 6845566 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7479. Min Act: -0.1700
Data Index: 49361 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7479. Min Act: -0.1700
Data Index: 4279120 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7479. Min Act: -0.1700
Data Index: 6460152 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7479. Min Act: -0.1700
Data Index: 5872714 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7166. Min Act: -0.1700
Data Index: 5199074 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3021947 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3459191 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7166. Min Act: -0.1700
Data Index: 1985265 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7166. Min Act: -0.1700
Data Index: 3747417 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7166. Min Act: -0.1700
Data Index: 3614408 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7166. Min Act: -0.1700
Data Index: 7559505 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7166. Min Act: -0.1700
Data Index: 7662242 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8104. Min Range: -5.8104
Max Act: 5.7166. Min Act: -0.1700
Data Index: 4912282 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19