Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5283 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.6293. Min Act: -0.1700
Data Index: 7549277 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.5980. Min Act: -0.1700
Data Index: 3938314 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.5668. Min Act: -0.1700
Data Index: 3410476 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.5355. Min Act: -0.1700
Data Index: 6185355 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.5668. Min Act: -0.1700
Data Index: 6869921 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.5355. Min Act: -0.1700
Data Index: 1439929 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.5355. Min Act: -0.1700
Data Index: 1728492 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4730. Min Act: -0.1700
Data Index: 656925 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4730. Min Act: -0.1700
Data Index: 227373 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4418. Min Act: -0.1700
Data Index: 4341058 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4730. Min Act: -0.1700
Data Index: 6020474 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4730. Min Act: -0.1700
Data Index: 8354311 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4418. Min Act: -0.1700
Data Index: 2474187 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4105. Min Act: -0.1700
Data Index: 3714625 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4418. Min Act: -0.1700
Data Index: 3075294 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4105. Min Act: -0.1700
Data Index: 7273640 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.3793. Min Act: -0.1700
Data Index: 3523143 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4105. Min Act: -0.1700
Data Index: 2146322 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4105. Min Act: -0.1700
Data Index: 4859390 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6293. Min Range: -6.6293
Max Act: 6.4105. Min Act: -0.1700
Data Index: 3608046 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19