Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.6447. Min Act: -0.1700
Data Index: 251783 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.5822. Min Act: -0.1700
Data Index: 4426523 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.6134. Min Act: -0.1700
Data Index: 4426525 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.5822. Min Act: -0.1700
Data Index: 4721213 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.5822. Min Act: -0.1700
Data Index: 5966806 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.5197. Min Act: -0.1700
Data Index: 3303740 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.5197. Min Act: -0.1700
Data Index: 3397126 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.4572. Min Act: -0.1700
Data Index: 5757843 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.4259. Min Act: -0.1700
Data Index: 8787822 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.4259. Min Act: -0.1700
Data Index: 7207460 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.4259. Min Act: -0.1700
Data Index: 124291 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.3947. Min Act: -0.1700
Data Index: 8596643 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.3634. Min Act: -0.1700
Data Index: 2811770 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.3634. Min Act: -0.1700
Data Index: 3964698 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.3634. Min Act: -0.1700
Data Index: 5517044 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.3634. Min Act: -0.1700
Data Index: 1308124 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.3634. Min Act: -0.1700
Data Index: 901370 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.3322. Min Act: -0.1700
Data Index: 2152795 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.3322. Min Act: -0.1700
Data Index: 5034149 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6447. Min Range: -6.6447
Max Act: 6.3322. Min Act: -0.1700
Data Index: 2595857 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19