Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3687 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.7606. Min Act: -0.1700
Data Index: 5274624 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.6981. Min Act: -0.1700
Data Index: 4410915 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.6668. Min Act: -0.1700
Data Index: 4410916 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.5418. Min Act: -0.1700
Data Index: 4410910 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.5106. Min Act: -0.1700
Data Index: 6359311 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.5106. Min Act: -0.1700
Data Index: 5320949 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.4793. Min Act: -0.1700
Data Index: 27671 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.4793. Min Act: -0.1700
Data Index: 4620055 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.4793. Min Act: -0.1700
Data Index: 7018089 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.5106. Min Act: -0.1700
Data Index: 1511533 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.4168. Min Act: -0.1700
Data Index: 8139737 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.4168. Min Act: -0.1700
Data Index: 3980724 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.4168. Min Act: -0.1700
Data Index: 75235 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.4168. Min Act: -0.1700
Data Index: 3970612 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.3856. Min Act: -0.1700
Data Index: 3828816 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.3856. Min Act: -0.1700
Data Index: 7472929 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.3543. Min Act: -0.1700
Data Index: 2551858 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.3543. Min Act: -0.1700
Data Index: 203466 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.3543. Min Act: -0.1700
Data Index: 3975874 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7606. Min Range: -6.7606
Max Act: 6.3231. Min Act: -0.1700
Data Index: 6684601 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19