Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.9233. Min Act: -0.1700
Data Index: 3280382 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.9233. Min Act: -0.1700
Data Index: 1626057 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.9233. Min Act: -0.1700
Data Index: 659319 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.9546. Min Act: -0.1700
Data Index: 4831774 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.8920. Min Act: -0.1700
Data Index: 2380921 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.8920. Min Act: -0.1700
Data Index: 6820472 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.8608. Min Act: -0.1700
Data Index: 865050 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.8608. Min Act: -0.1700
Data Index: 3645318 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.8295. Min Act: -0.1700
Data Index: 3156461 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7982. Min Act: -0.1700
Data Index: 5203622 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7982. Min Act: -0.1700
Data Index: 5105114 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7982. Min Act: -0.1700
Data Index: 734029 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7982. Min Act: -0.1700
Data Index: 1431912 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7982. Min Act: -0.1700
Data Index: 1402798 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7669. Min Act: -0.1700
Data Index: 5680730 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7669. Min Act: -0.1700
Data Index: 5711846 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7669. Min Act: -0.1700
Data Index: 2252500 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7982. Min Act: -0.1700
Data Index: 5534297 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7669. Min Act: -0.1700
Data Index: 1202689 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9546. Min Range: -3.9546
Max Act: 3.7669. Min Act: -0.1700
Data Index: 5910563 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19