Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.8673. Min Act: -0.1700
Data Index: 8447844 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.6486. Min Act: -0.1700
Data Index: 7022655 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.6173. Min Act: -0.1700
Data Index: 7104561 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.5236. Min Act: -0.1700
Data Index: 5570486 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.4611. Min Act: -0.1700
Data Index: 3753088 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.3986. Min Act: -0.1700
Data Index: 594092 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.3361. Min Act: -0.1700
Data Index: 6090232 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.2736. Min Act: -0.1700
Data Index: 8030925 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.2736. Min Act: -0.1700
Data Index: 3536147 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.2423. Min Act: -0.1700
Data Index: 6838814 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.2736. Min Act: -0.1700
Data Index: 4302176 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.2423. Min Act: -0.1700
Data Index: 1074077 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.1798. Min Act: -0.1700
Data Index: 2872402 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.2423. Min Act: -0.1700
Data Index: 8211270 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.1798. Min Act: -0.1700
Data Index: 5918303 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.1798. Min Act: -0.1700
Data Index: 6033618 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.1798. Min Act: -0.1700
Data Index: 552352 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.1486. Min Act: -0.1700
Data Index: 4155902 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.1486. Min Act: -0.1700
Data Index: 7735908 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8673. Min Range: -6.8673
Max Act: 6.1486. Min Act: -0.1700
Data Index: 4827050 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19