Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4656 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.8141. Min Act: -0.1700
Data Index: 4459650 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.6579. Min Act: -0.1700
Data Index: 7182771 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.6579. Min Act: -0.1700
Data Index: 4036822 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.5329. Min Act: -0.1700
Data Index: 2124486 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.5329. Min Act: -0.1700
Data Index: 3935547 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.5329. Min Act: -0.1700
Data Index: 1922024 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.5016. Min Act: -0.1700
Data Index: 7069417 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4704. Min Act: -0.1700
Data Index: 4405089 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.5016. Min Act: -0.1700
Data Index: 1723561 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4704. Min Act: -0.1700
Data Index: 559096 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4704. Min Act: -0.1700
Data Index: 2062376 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4704. Min Act: -0.1700
Data Index: 5364967 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4391. Min Act: -0.1700
Data Index: 8437847 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4704. Min Act: -0.1700
Data Index: 636617 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4704. Min Act: -0.1700
Data Index: 2873861 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4391. Min Act: -0.1700
Data Index: 5766423 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4704. Min Act: -0.1700
Data Index: 5386623 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4079. Min Act: -0.1700
Data Index: 6388887 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.4079. Min Act: -0.1700
Data Index: 235768 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8141. Min Range: -4.8141
Max Act: 4.3766. Min Act: -0.1700
Data Index: 2622567 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19