Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4079 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2091. Min Range: -5.2091
Max Act: 5.2091. Min Act: -0.1700
Data Index: 5589296 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2091. Min Range: -5.2091
Max Act: 5.1466. Min Act: -0.1700
Data Index: 7166579 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2091. Min Range: -5.2091
Max Act: 5.0528. Min Act: -0.1700
Data Index: 8002979 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.9903. Min Act: -0.1700
Data Index: 2520021 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.9591. Min Act: -0.1700
Data Index: 5873567 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.9903. Min Act: -0.1700
Data Index: 3866357 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.9591. Min Act: -0.1700
Data Index: 1243428 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.9591. Min Act: -0.1700
Data Index: 7803825 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8966. Min Act: -0.1700
Data Index: 753985 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.9278. Min Act: -0.1700
Data Index: 7928932 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8966. Min Act: -0.1700
Data Index: 6692714 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8966. Min Act: -0.1700
Data Index: 7508431 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8966. Min Act: -0.1700
Data Index: 90160 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8653. Min Act: -0.1700
Data Index: 2646949 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8653. Min Act: -0.1700
Data Index: 6080311 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8653. Min Act: -0.1700
Data Index: 1005393 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8653. Min Act: -0.1700
Data Index: 5386521 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8341. Min Act: -0.1700
Data Index: 173005 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8341. Min Act: -0.1700
Data Index: 991172 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2091. Min Range: -5.2091
Max Act: 4.8341. Min Act: -0.1700
Data Index: 720827 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19