Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4842 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.4921. Min Act: -0.1700
Data Index: 1377093 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.4296. Min Act: -0.1700
Data Index: 1476120 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.2109. Min Act: -0.1700
Data Index: 859757 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.1484. Min Act: -0.1700
Data Index: 7358817 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.0859. Min Act: -0.1700
Data Index: 7121869 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.0546. Min Act: -0.1700
Data Index: 7298664 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.0546. Min Act: -0.1700
Data Index: 658776 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.0234. Min Act: -0.1700
Data Index: 8759297 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.0546. Min Act: -0.1700
Data Index: 1820008 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4921. Min Range: -6.4921
Max Act: 6.0234. Min Act: -0.1700
Data Index: 6996615 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.9921. Min Act: -0.1700
Data Index: 6729955 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.9921. Min Act: -0.1700
Data Index: 7955084 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.9609. Min Act: -0.1700
Data Index: 2846414 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.9609. Min Act: -0.1700
Data Index: 5056406 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.9609. Min Act: -0.1700
Data Index: 4785198 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.9609. Min Act: -0.1700
Data Index: 11802 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.9296. Min Act: -0.1700
Data Index: 175608 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.9296. Min Act: -0.1700
Data Index: 931348 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.9296. Min Act: -0.1700
Data Index: 7906137 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4921. Min Range: -6.4921
Max Act: 5.8984. Min Act: -0.1700
Data Index: 4155593 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19