Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.2249. Min Act: -0.1700
Data Index: 7799453 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.2072. Min Act: -0.1699
Data Index: 3127571 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1896. Min Act: -0.1698
Data Index: 3711834 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1720. Min Act: -0.1700
Data Index: 3013652 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1720. Min Act: -0.1700
Data Index: 6839588 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1720. Min Act: -0.1695
Data Index: 6220191 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1896. Min Act: -0.1700
Data Index: 6688321 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1369. Min Act: -0.1700
Data Index: 6506062 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1193. Min Act: -0.1700
Data Index: 7740132 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1193. Min Act: -0.1700
Data Index: 5343249 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1369. Min Act: -0.1697
Data Index: 13831 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1018. Min Act: -0.1700
Data Index: 6203843 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.1193. Min Act: -0.1691
Data Index: 2773336 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.0668. Min Act: -0.1700
Data Index: 755901 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.0668. Min Act: -0.1700
Data Index: 1726842 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.0843. Min Act: -0.1700
Data Index: 2433561 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.0843. Min Act: -0.1700
Data Index: 5369754 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.0843. Min Act: -0.1700
Data Index: 5853234 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.0668. Min Act: -0.1700
Data Index: 6926111 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2249. Min Range: -1.2249
Max Act: 1.0581. Min Act: -0.1698
Data Index: 3415050 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19