Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.6062. Min Act: -0.1700
Data Index: 4402618 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.5905. Min Act: -0.1699
Data Index: 3310924 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.5748. Min Act: -0.1696
Data Index: 3703961 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.5593. Min Act: -0.1692
Data Index: 3452188 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.5286. Min Act: -0.1700
Data Index: 6787521 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.5286. Min Act: -0.1695
Data Index: 3301807 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.5134. Min Act: -0.1691
Data Index: 7095713 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.5059. Min Act: -0.1653
Data Index: 4741504 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.5059. Min Act: -0.1698
Data Index: 6947804 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4984. Min Act: -0.1700
Data Index: 3454611 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.5059. Min Act: -0.1700
Data Index: 921696 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4909. Min Act: -0.1700
Data Index: 5482984 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4909. Min Act: -0.1697
Data Index: 8131498 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4984. Min Act: -0.1699
Data Index: 5983192 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4909. Min Act: -0.1696
Data Index: 50572 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4909. Min Act: -0.1700
Data Index: 5930165 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4984. Min Act: -0.1661
Data Index: 4340820 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4909. Min Act: -0.1691
Data Index: 7747911 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4909. Min Act: -0.1685
Data Index: 5835300 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6062. Min Range: -0.6062
Max Act: 0.4909. Min Act: -0.1700
Data Index: 4805766 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19