Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.5908. Min Act: -0.1700
Data Index: 3194071 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.5595. Min Act: -0.1700
Data Index: 8118144 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.5125. Min Act: -0.1700
Data Index: 2452926 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4969. Min Act: -0.1700
Data Index: 5703673 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4969. Min Act: -0.1700
Data Index: 5261399 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4969. Min Act: -0.1700
Data Index: 8051848 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4812. Min Act: -0.1700
Data Index: 1898329 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4655. Min Act: -0.1700
Data Index: 8135151 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4342. Min Act: -0.1700
Data Index: 1863436 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4499. Min Act: -0.1700
Data Index: 899977 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4185. Min Act: -0.1700
Data Index: 4287855 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4029. Min Act: -0.1700
Data Index: 8099303 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4185. Min Act: -0.1700
Data Index: 2236408 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3715. Min Act: -0.1700
Data Index: 724144 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3558. Min Act: -0.1700
Data Index: 7084004 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3558. Min Act: -0.1700
Data Index: 7196983 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3558. Min Act: -0.1700
Data Index: 3072236 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3401. Min Act: -0.1700
Data Index: 7276750 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3558. Min Act: -0.1700
Data Index: 4020866 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3401. Min Act: -0.1700
Data Index: 2201846 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19