Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1123 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.5452. Min Act: -0.1700
Data Index: 6212453 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.1702. Min Act: -0.1700
Data Index: 7790128 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.1702. Min Act: -0.1700
Data Index: 8674768 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.0765. Min Act: -0.1700
Data Index: 4962322 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.0765. Min Act: -0.1700
Data Index: 5639534 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.0765. Min Act: -0.1700
Data Index: 850269 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.0765. Min Act: -0.1700
Data Index: 5400377 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.0140. Min Act: -0.1700
Data Index: 732689 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.0452. Min Act: -0.1700
Data Index: 7791035 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.0452. Min Act: -0.1700
Data Index: 7204697 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9827. Min Act: -0.1700
Data Index: 6079141 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.0140. Min Act: -0.1700
Data Index: 6520737 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.0140. Min Act: -0.1700
Data Index: 753636 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9827. Min Act: -0.1700
Data Index: 2497673 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9827. Min Act: -0.1700
Data Index: 5365001 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9515. Min Act: -0.1700
Data Index: 2783028 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9515. Min Act: -0.1700
Data Index: 8230860 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9515. Min Act: -0.1700
Data Index: 8067613 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9827. Min Act: -0.1700
Data Index: 5986002 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.8890. Min Act: -0.1700
Data Index: 7757268 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19