Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1584 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.9942. Min Act: -0.1700
Data Index: 601320 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.9317. Min Act: -0.1700
Data Index: 6794607 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.6817. Min Act: -0.1700
Data Index: 5477751 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.6817. Min Act: -0.1700
Data Index: 1656455 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.4942. Min Act: -0.1700
Data Index: 6277383 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.5567. Min Act: -0.1700
Data Index: 4427822 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.4942. Min Act: -0.1700
Data Index: 1504937 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.4317. Min Act: -0.1700
Data Index: 4312382 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.4317. Min Act: -0.1700
Data Index: 1378579 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.3067. Min Act: -0.1700
Data Index: 5227153 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.3067. Min Act: -0.1700
Data Index: 7691901 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.2442. Min Act: -0.1700
Data Index: 4350525 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.2442. Min Act: -0.1700
Data Index: 4050684 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.1504. Min Act: -0.1700
Data Index: 2556738 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.1817. Min Act: -0.1700
Data Index: 2924181 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.1817. Min Act: -0.1700
Data Index: 8667684 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.1504. Min Act: -0.1700
Data Index: 3368164 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.1504. Min Act: -0.1700
Data Index: 6794143 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.1192. Min Act: -0.1700
Data Index: 8561219 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9942. Min Range: -8.9942
Max Act: 8.1192. Min Act: -0.1700
Data Index: 5669613 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19