Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.7011. Min Act: -0.1700
Data Index: 1725800 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.6073. Min Act: -0.1700
Data Index: 2952453 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.5448. Min Act: -0.1700
Data Index: 1075426 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.5448. Min Act: -0.1700
Data Index: 3634632 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.4823. Min Act: -0.1700
Data Index: 2819649 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.4511. Min Act: -0.1700
Data Index: 8005206 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.3886. Min Act: -0.1700
Data Index: 2737229 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.3573. Min Act: -0.1700
Data Index: 8187240 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.3886. Min Act: -0.1700
Data Index: 2762857 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.3573. Min Act: -0.1700
Data Index: 6260922 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2948. Min Act: -0.1700
Data Index: 6713543 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2636. Min Act: -0.1700
Data Index: 3049727 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2636. Min Act: -0.1700
Data Index: 1071255 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2323. Min Act: -0.1700
Data Index: 1500626 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2011. Min Act: -0.1700
Data Index: 2739100 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2323. Min Act: -0.1700
Data Index: 3528951 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2011. Min Act: -0.1700
Data Index: 5595529 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2011. Min Act: -0.1700
Data Index: 5901865 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2011. Min Act: -0.1700
Data Index: 1538521 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7011. Min Range: -5.7011
Max Act: 5.2011. Min Act: -0.1700
Data Index: 7893623 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19