Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.6359. Min Act: -0.1700
Data Index: 1322361 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.4796. Min Act: -0.1700
Data Index: 1119471 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.4171. Min Act: -0.1700
Data Index: 2097679 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.2921. Min Act: -0.1700
Data Index: 784431 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.2609. Min Act: -0.1700
Data Index: 2417084 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.2609. Min Act: -0.1700
Data Index: 7065610 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.1984. Min Act: -0.1700
Data Index: 3776551 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.1671. Min Act: -0.1700
Data Index: 8122458 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.1671. Min Act: -0.1700
Data Index: 7046035 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.1359. Min Act: -0.1700
Data Index: 5147676 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.1671. Min Act: -0.1700
Data Index: 1149438 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.1359. Min Act: -0.1700
Data Index: 6993912 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.1359. Min Act: -0.1700
Data Index: 4995254 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.0421. Min Act: -0.1700
Data Index: 6499160 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.0421. Min Act: -0.1700
Data Index: 4843738 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.0421. Min Act: -0.1700
Data Index: 5011125 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.0421. Min Act: -0.1700
Data Index: 1198520 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6359. Min Range: -6.6359
Max Act: 5.9796. Min Act: -0.1700
Data Index: 3861424 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.0109. Min Act: -0.1700
Data Index: 3811520 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6359. Min Range: -6.6359
Max Act: 6.0109. Min Act: -0.1700
Data Index: 4191470 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19