Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1650. Min Range: -5.1650
Max Act: 5.1650. Min Act: -0.1700
Data Index: 4330470 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1650. Min Range: -5.1650
Max Act: 5.1650. Min Act: -0.1700
Data Index: 7221790 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1650. Min Range: -5.1650
Max Act: 5.0713. Min Act: -0.1700
Data Index: 6519256 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1650. Min Range: -5.1650
Max Act: 5.0400. Min Act: -0.1700
Data Index: 1556431 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1650. Min Range: -5.1650
Max Act: 5.0088. Min Act: -0.1700
Data Index: 535100 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.9775. Min Act: -0.1700
Data Index: 6669424 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.9463. Min Act: -0.1700
Data Index: 7074129 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.9463. Min Act: -0.1700
Data Index: 1455283 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.9463. Min Act: -0.1700
Data Index: 5557850 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.9150. Min Act: -0.1700
Data Index: 496193 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8838. Min Act: -0.1700
Data Index: 5369404 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8525. Min Act: -0.1700
Data Index: 3653067 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8525. Min Act: -0.1700
Data Index: 376967 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8525. Min Act: -0.1700
Data Index: 2393242 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8525. Min Act: -0.1700
Data Index: 7340345 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8525. Min Act: -0.1700
Data Index: 1854881 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8525. Min Act: -0.1700
Data Index: 7181084 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8525. Min Act: -0.1700
Data Index: 6088996 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8525. Min Act: -0.1700
Data Index: 3131691 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1650. Min Range: -5.1650
Max Act: 4.8525. Min Act: -0.1700
Data Index: 3724858 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19