Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5432 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0379. Min Range: -7.0379
Max Act: 7.0379. Min Act: -0.1700
Data Index: 2941710 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.8817. Min Act: -0.1700
Data Index: 3365851 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.6317. Min Act: -0.1700
Data Index: 6832352 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.6004. Min Act: -0.1700
Data Index: 8069790 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.6004. Min Act: -0.1700
Data Index: 7581717 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.5379. Min Act: -0.1700
Data Index: 7558351 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.5379. Min Act: -0.1700
Data Index: 1617744 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.4754. Min Act: -0.1700
Data Index: 1949168 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.4754. Min Act: -0.1700
Data Index: 2010514 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.4442. Min Act: -0.1700
Data Index: 1572510 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.4442. Min Act: -0.1700
Data Index: 6586362 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.3817. Min Act: -0.1700
Data Index: 7899841 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.3817. Min Act: -0.1700
Data Index: 318222 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.3817. Min Act: -0.1700
Data Index: 7778674 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.3192. Min Act: -0.1700
Data Index: 4783894 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.3504. Min Act: -0.1700
Data Index: 7452795 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.3504. Min Act: -0.1700
Data Index: 5205504 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.3504. Min Act: -0.1700
Data Index: 2961517 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.3504. Min Act: -0.1700
Data Index: 218044 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0379. Min Range: -7.0379
Max Act: 6.3192. Min Act: -0.1700
Data Index: 2388891 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19