Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3130. Min Range: -6.3130
Max Act: 6.2505. Min Act: -0.1700
Data Index: 7300267 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3130. Min Range: -6.3130
Max Act: 6.3130. Min Act: -0.1700
Data Index: 2982239 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.9693. Min Act: -0.1700
Data Index: 8802958 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.9693. Min Act: -0.1700
Data Index: 7215190 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.9380. Min Act: -0.1700
Data Index: 7970000 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.9068. Min Act: -0.1700
Data Index: 4458394 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.7818. Min Act: -0.1700
Data Index: 459406 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.8130. Min Act: -0.1700
Data Index: 6914065 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.7818. Min Act: -0.1700
Data Index: 6620873 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.7818. Min Act: -0.1700
Data Index: 2982240 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.7818. Min Act: -0.1700
Data Index: 691915 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.7505. Min Act: -0.1700
Data Index: 5254836 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.7193. Min Act: -0.1700
Data Index: 5764402 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2440953 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.6880. Min Act: -0.1700
Data Index: 5448184 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.6568. Min Act: -0.1699
Data Index: 2288406 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.6880. Min Act: -0.1700
Data Index: 8733478 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.6568. Min Act: -0.1700
Data Index: 3918571 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.6568. Min Act: -0.1698
Data Index: 4961951 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3130. Min Range: -6.3130
Max Act: 5.6568. Min Act: -0.1700
Data Index: 4071799 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19