Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5266 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.9942. Min Act: -0.1700
Data Index: 1031723 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.9317. Min Act: -0.1700
Data Index: 837314 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.9004. Min Act: -0.1700
Data Index: 3658019 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.8067. Min Act: -0.1700
Data Index: 1632376 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.7754. Min Act: -0.1700
Data Index: 3608802 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.7129. Min Act: -0.1700
Data Index: 5341838 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.7129. Min Act: -0.1700
Data Index: 527705 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.7129. Min Act: -0.1700
Data Index: 5377636 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.6817. Min Act: -0.1700
Data Index: 3467346 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.6192. Min Act: -0.1700
Data Index: 7690445 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.5567. Min Act: -0.1700
Data Index: 1496096 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.5567. Min Act: -0.1700
Data Index: 5680952 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.4942. Min Act: -0.1700
Data Index: 1871507 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.4942. Min Act: -0.1700
Data Index: 1631946 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.4942. Min Act: -0.1700
Data Index: 5513849 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.4942. Min Act: -0.1700
Data Index: 4207745 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.4942. Min Act: -0.1700
Data Index: 6268469 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.4317. Min Act: -0.1700
Data Index: 3721502 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.4317. Min Act: -0.1700
Data Index: 4143799 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9942. Min Range: -6.9942
Max Act: 6.4317. Min Act: -0.1700
Data Index: 290441 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19