Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.2940. Min Act: -0.1700
Data Index: 5068464 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.3252. Min Act: -0.1700
Data Index: 2551789 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.3252. Min Act: -0.1700
Data Index: 935594 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.3252. Min Act: -0.1700
Data Index: 4007100 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.2627. Min Act: -0.1700
Data Index: 3216021 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.2315. Min Act: -0.1700
Data Index: 7140443 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.2315. Min Act: -0.1700
Data Index: 407461 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.2002. Min Act: -0.1700
Data Index: 4397105 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.2315. Min Act: -0.1700
Data Index: 1116005 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.2002. Min Act: -0.1700
Data Index: 7045073 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.2002. Min Act: -0.1700
Data Index: 3119022 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.1690. Min Act: -0.1700
Data Index: 1604758 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.1690. Min Act: -0.1700
Data Index: 7399225 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.1377. Min Act: -0.1700
Data Index: 3218979 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.1377. Min Act: -0.1700
Data Index: 5590288 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.1377. Min Act: -0.1700
Data Index: 1458447 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.1065. Min Act: -0.1700
Data Index: 860581 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.1065. Min Act: -0.1700
Data Index: 6198200 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.1065. Min Act: -0.1700
Data Index: 7013902 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3252. Min Range: -6.3252
Max Act: 6.1377. Min Act: -0.1700
Data Index: 6520911 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19