Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4932 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.7293. Min Act: -0.1700
Data Index: 2146702 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.5106. Min Act: -0.1700
Data Index: 5505179 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.4481. Min Act: -0.1700
Data Index: 720688 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.4168. Min Act: -0.1700
Data Index: 8383365 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.4481. Min Act: -0.1700
Data Index: 4852419 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.3856. Min Act: -0.1700
Data Index: 6482347 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.3543. Min Act: -0.1700
Data Index: 5145374 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.3543. Min Act: -0.1700
Data Index: 5968011 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.2918. Min Act: -0.1700
Data Index: 1904832 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.3231. Min Act: -0.1700
Data Index: 3028106 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.3231. Min Act: -0.1700
Data Index: 2600367 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.2918. Min Act: -0.1700
Data Index: 6663563 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.2918. Min Act: -0.1700
Data Index: 7083775 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.3231. Min Act: -0.1700
Data Index: 954714 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.2918. Min Act: -0.1700
Data Index: 4852425 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.2918. Min Act: -0.1700
Data Index: 5038452 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.2918. Min Act: -0.1700
Data Index: 4788693 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.2606. Min Act: -0.1700
Data Index: 4813583 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.2918. Min Act: -0.1700
Data Index: 5607349 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7293. Min Range: -5.7293
Max Act: 5.2606. Min Act: -0.1700
Data Index: 1059569 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19