Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4107. Min Range: -8.4107
Max Act: 8.4107. Min Act: -0.1700
Data Index: 5520840 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4107. Min Range: -8.4107
Max Act: 8.2857. Min Act: -0.1700
Data Index: 8616546 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4107. Min Range: -8.4107
Max Act: 8.2857. Min Act: -0.1700
Data Index: 6476560 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4107. Min Range: -8.4107
Max Act: 8.2857. Min Act: -0.1700
Data Index: 7448054 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4107. Min Range: -8.4107
Max Act: 8.1607. Min Act: -0.1700
Data Index: 3907689 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4107. Min Range: -8.4107
Max Act: 8.0357. Min Act: -0.1700
Data Index: 464646 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.9732. Min Act: -0.1700
Data Index: 351110 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.9732. Min Act: -0.1700
Data Index: 4993927 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.9732. Min Act: -0.1700
Data Index: 4010791 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.8482. Min Act: -0.1700
Data Index: 8058499 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.8482. Min Act: -0.1700
Data Index: 5035775 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.8482. Min Act: -0.1700
Data Index: 3268270 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.8482. Min Act: -0.1700
Data Index: 542185 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.8482. Min Act: -0.1700
Data Index: 8496984 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.7857. Min Act: -0.1700
Data Index: 170219 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.7857. Min Act: -0.1700
Data Index: 268752 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.6607. Min Act: -0.1700
Data Index: 4081213 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.7232. Min Act: -0.1700
Data Index: 8473279 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.7232. Min Act: -0.1700
Data Index: 5933803 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4107. Min Range: -8.4107
Max Act: 7.5982. Min Act: -0.1700
Data Index: 2395084 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19