Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1191 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.7751. Min Act: -0.1700
Data Index: 1657968 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.6501. Min Act: -0.1700
Data Index: 5687273 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.6501. Min Act: -0.1700
Data Index: 2704530 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.7126. Min Act: -0.1700
Data Index: 6902980 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5876. Min Act: -0.1700
Data Index: 8822865 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5876. Min Act: -0.1700
Data Index: 128277 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5563. Min Act: -0.1700
Data Index: 3248540 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5563. Min Act: -0.1700
Data Index: 7761486 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5563. Min Act: -0.1700
Data Index: 2206140 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5563. Min Act: -0.1700
Data Index: 496851 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5563. Min Act: -0.1700
Data Index: 2115395 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5563. Min Act: -0.1700
Data Index: 4896407 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5251. Min Act: -0.1700
Data Index: 1078929 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5251. Min Act: -0.1700
Data Index: 7072297 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5251. Min Act: -0.1698
Data Index: 1559599 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.4938. Min Act: -0.1700
Data Index: 8325058 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5251. Min Act: -0.1700
Data Index: 6015607 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.5251. Min Act: -0.1700
Data Index: 2542782 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.4938. Min Act: -0.1700
Data Index: 7723574 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7751. Min Range: -6.7751
Max Act: 6.4938. Min Act: -0.1700
Data Index: 389294 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19