Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6166 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.3629. Min Act: -0.1700
Data Index: 4636477 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.2692. Min Act: -0.1700
Data Index: 5870585 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.2692. Min Act: -0.1700
Data Index: 1929479 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.2379. Min Act: -0.1700
Data Index: 6158012 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.2379. Min Act: -0.1700
Data Index: 6577722 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.2379. Min Act: -0.1700
Data Index: 4419023 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.2379. Min Act: -0.1700
Data Index: 648238 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.2067. Min Act: -0.1700
Data Index: 8624388 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.2067. Min Act: -0.1700
Data Index: 30969 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 6520903 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 6529442 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 8731853 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 1050469 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1754. Min Act: -0.1700
Data Index: 576152 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1442. Min Act: -0.1700
Data Index: 8035222 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1442. Min Act: -0.1700
Data Index: 2708602 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1442. Min Act: -0.1700
Data Index: 7785538 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1129. Min Act: -0.1700
Data Index: 3744329 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1442. Min Act: -0.1700
Data Index: 925490 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3629. Min Range: -4.3629
Max Act: 4.1442. Min Act: -0.1700
Data Index: 6412966 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19