Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2879 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8143. Min Range: -6.8143
Max Act: 6.8143. Min Act: -0.1700
Data Index: 8178637 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8143. Min Range: -6.8143
Max Act: 6.2518. Min Act: -0.1700
Data Index: 5701823 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8143. Min Range: -6.8143
Max Act: 6.1893. Min Act: -0.1700
Data Index: 7140402 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8143. Min Range: -6.8143
Max Act: 6.0643. Min Act: -0.1700
Data Index: 3212088 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8143. Min Range: -6.8143
Max Act: 6.0331. Min Act: -0.1700
Data Index: 3150211 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9706. Min Act: -0.1700
Data Index: 1843443 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9706. Min Act: -0.1700
Data Index: 1441536 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 7488592 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 1616633 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 5972340 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 7223690 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 5392825 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9393. Min Act: -0.1700
Data Index: 1242453 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9081. Min Act: -0.1700
Data Index: 8809388 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.9081. Min Act: -0.1700
Data Index: 1940979 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.8768. Min Act: -0.1700
Data Index: 5781107 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.8456. Min Act: -0.1700
Data Index: 3520750 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.8456. Min Act: -0.1700
Data Index: 8134140 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.8143. Min Act: -0.1700
Data Index: 6817898 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8143. Min Range: -6.8143
Max Act: 5.8456. Min Act: -0.1700
Data Index: 3681735 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19