Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.1794. Min Act: -0.1700
Data Index: 2629078 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.1169. Min Act: -0.1700
Data Index: 8470248 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.0857. Min Act: -0.1700
Data Index: 3287860 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.1169. Min Act: -0.1700
Data Index: 6619795 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.0544. Min Act: -0.1700
Data Index: 1314507 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.0544. Min Act: -0.1700
Data Index: 5861183 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.0232. Min Act: -0.1700
Data Index: 3261707 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.0232. Min Act: -0.1700
Data Index: 7612044 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.0544. Min Act: -0.1700
Data Index: 5684537 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.0232. Min Act: -0.1700
Data Index: 5820383 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1794. Min Range: -5.1794
Max Act: 5.0232. Min Act: -0.1700
Data Index: 1863741 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1794. Min Range: -5.1794
Max Act: 4.9919. Min Act: -0.1700
Data Index: 7253365 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1794. Min Range: -5.1794
Max Act: 4.9919. Min Act: -0.1700
Data Index: 2776127 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1794. Min Range: -5.1794
Max Act: 4.9607. Min Act: -0.1700
Data Index: 4481721 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1794. Min Range: -5.1794
Max Act: 4.9607. Min Act: -0.1700
Data Index: 4756659 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1794. Min Range: -5.1794
Max Act: 4.9607. Min Act: -0.1700
Data Index: 4115278 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1794. Min Range: -5.1794
Max Act: 4.9607. Min Act: -0.1700
Data Index: 5361239 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1794. Min Range: -5.1794
Max Act: 4.9607. Min Act: -0.1700
Data Index: 2201456 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1794. Min Range: -5.1794
Max Act: 4.9294. Min Act: -0.1700
Data Index: 6742446 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1794. Min Range: -5.1794
Max Act: 4.8982. Min Act: -0.1700
Data Index: 1265685 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19