Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2787. Min Range: -6.2787
Max Act: 6.2787. Min Act: -0.1700
Data Index: 3850895 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2787. Min Range: -6.2787
Max Act: 6.0912. Min Act: -0.1700
Data Index: 7716422 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.9037. Min Act: -0.1700
Data Index: 4709091 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.8412. Min Act: -0.1700
Data Index: 1902391 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.8100. Min Act: -0.1700
Data Index: 3349289 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.8100. Min Act: -0.1700
Data Index: 2883104 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.7787. Min Act: -0.1700
Data Index: 4472757 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.7787. Min Act: -0.1700
Data Index: 1152808 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.7787. Min Act: -0.1700
Data Index: 1587608 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.7162. Min Act: -0.1700
Data Index: 3986502 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.7162. Min Act: -0.1700
Data Index: 3838926 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.7162. Min Act: -0.1700
Data Index: 4434258 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.7162. Min Act: -0.1700
Data Index: 8669684 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.6850. Min Act: -0.1700
Data Index: 1078771 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.7162. Min Act: -0.1700
Data Index: 6703325 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.6850. Min Act: -0.1700
Data Index: 4155951 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.6850. Min Act: -0.1700
Data Index: 8335701 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.6850. Min Act: -0.1700
Data Index: 317464 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.6850. Min Act: -0.1700
Data Index: 3992191 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2787. Min Range: -6.2787
Max Act: 5.6537. Min Act: -0.1700
Data Index: 7334850 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19