Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1622 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.7261. Min Act: -0.1700
Data Index: 562256 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.5386. Min Act: -0.1700
Data Index: 5688585 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.4761. Min Act: -0.1700
Data Index: 671903 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.5074. Min Act: -0.1700
Data Index: 273033 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.3824. Min Act: -0.1700
Data Index: 7732063 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.2886. Min Act: -0.1700
Data Index: 1601207 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.2261. Min Act: -0.1700
Data Index: 8029978 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1324. Min Act: -0.1700
Data Index: 5837675 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1324. Min Act: -0.1700
Data Index: 782776 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1636. Min Act: -0.1700
Data Index: 2445885 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.1011. Min Act: -0.1700
Data Index: 6714330 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0699. Min Act: -0.1700
Data Index: 6950012 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0699. Min Act: -0.1700
Data Index: 2020884 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0386. Min Act: -0.1700
Data Index: 5252149 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0386. Min Act: -0.1700
Data Index: 1744835 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0074. Min Act: -0.1700
Data Index: 5479023 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0074. Min Act: -0.1700
Data Index: 1728967 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7261. Min Range: -6.7261
Max Act: 5.9761. Min Act: -0.1700
Data Index: 1322497 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0074. Min Act: -0.1700
Data Index: 4730612 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7261. Min Range: -6.7261
Max Act: 6.0074. Min Act: -0.1700
Data Index: 1814077 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19