Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4621 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5474. Min Range: -8.5474
Max Act: 8.5474. Min Act: -0.1700
Data Index: 8192933 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5474. Min Range: -8.5474
Max Act: 8.4849. Min Act: -0.1700
Data Index: 4168545 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5474. Min Range: -8.5474
Max Act: 8.0474. Min Act: -0.1700
Data Index: 7826934 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.9849. Min Act: -0.1700
Data Index: 283264 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.9224. Min Act: -0.1700
Data Index: 5215298 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.9224. Min Act: -0.1700
Data Index: 2054819 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.8599. Min Act: -0.1700
Data Index: 3055523 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7974. Min Act: -0.1700
Data Index: 3544800 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7974. Min Act: -0.1700
Data Index: 99815 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.8599. Min Act: -0.1700
Data Index: 6569504 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.9224. Min Act: -0.1700
Data Index: 1428067 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.8599. Min Act: -0.1700
Data Index: 7918574 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7974. Min Act: -0.1700
Data Index: 80950 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7974. Min Act: -0.1700
Data Index: 1375355 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7974. Min Act: -0.1700
Data Index: 7552447 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7974. Min Act: -0.1700
Data Index: 1503486 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7974. Min Act: -0.1700
Data Index: 2319027 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7974. Min Act: -0.1700
Data Index: 2999114 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7349. Min Act: -0.1700
Data Index: 4726691 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5474. Min Range: -8.5474
Max Act: 7.7349. Min Act: -0.1700
Data Index: 5889734 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19