Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4591 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1396. Min Range: -7.1396
Max Act: 7.1396. Min Act: -0.1700
Data Index: 2224371 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1396. Min Range: -7.1396
Max Act: 7.1083. Min Act: -0.1700
Data Index: 4984917 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1396. Min Range: -7.1396
Max Act: 7.0146. Min Act: -0.1700
Data Index: 3146015 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.9833. Min Act: -0.1700
Data Index: 4422884 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8896. Min Act: -0.1700
Data Index: 8492787 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.9208. Min Act: -0.1700
Data Index: 4327444 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8896. Min Act: -0.1700
Data Index: 4986756 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8583. Min Act: -0.1700
Data Index: 1607276 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8583. Min Act: -0.1700
Data Index: 6395776 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8583. Min Act: -0.1700
Data Index: 3855209 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8583. Min Act: -0.1700
Data Index: 3793646 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8583. Min Act: -0.1700
Data Index: 1231490 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8583. Min Act: -0.1700
Data Index: 987910 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.7958. Min Act: -0.1700
Data Index: 7713553 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8271. Min Act: -0.1700
Data Index: 6217760 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.8271. Min Act: -0.1700
Data Index: 887854 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.7958. Min Act: -0.1700
Data Index: 5293571 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.7958. Min Act: -0.1700
Data Index: 5786591 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.7958. Min Act: -0.1700
Data Index: 6010289 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1396. Min Range: -7.1396
Max Act: 6.7958. Min Act: -0.1700
Data Index: 3392720 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19