Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1007. Min Range: -9.1007
Max Act: 9.1007. Min Act: -0.1700
Data Index: 1442588 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1007. Min Range: -9.1007
Max Act: 9.1007. Min Act: -0.1700
Data Index: 7460970 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.8507. Min Act: -0.1700
Data Index: 4816989 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.9132. Min Act: -0.1700
Data Index: 8718699 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.9132. Min Act: -0.1700
Data Index: 2836673 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.8507. Min Act: -0.1700
Data Index: 4236383 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.7257. Min Act: -0.1700
Data Index: 8453782 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.7882. Min Act: -0.1700
Data Index: 3273161 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6632. Min Act: -0.1700
Data Index: 3141268 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6632. Min Act: -0.1700
Data Index: 7827278 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6632. Min Act: -0.1700
Data Index: 6872697 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6632. Min Act: -0.1700
Data Index: 4109775 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6632. Min Act: -0.1700
Data Index: 994970 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6007. Min Act: -0.1700
Data Index: 7468290 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6007. Min Act: -0.1700
Data Index: 7367231 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6007. Min Act: -0.1700
Data Index: 6980793 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6632. Min Act: -0.1700
Data Index: 1425133 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6007. Min Act: -0.1700
Data Index: 8696016 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.6007. Min Act: -0.1700
Data Index: 2933662 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1007. Min Range: -9.1007
Max Act: 8.5382. Min Act: -0.1700
Data Index: 2471904 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19