Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0068. Min Range: -2.0068
Max Act: 2.0068. Min Act: -0.1688
Data Index: 4918922 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9899. Min Act: -0.1698
Data Index: 955742 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9814. Min Act: -0.1624
Data Index: 459204 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9729. Min Act: -0.1696
Data Index: 4196995 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9729. Min Act: -0.1667
Data Index: 1203947 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9645. Min Act: -0.1687
Data Index: 6333439 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9729. Min Act: -0.1669
Data Index: 7599747 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9560. Min Act: -0.1700
Data Index: 7001207 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9475. Min Act: -0.1589
Data Index: 2419044 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9475. Min Act: -0.1700
Data Index: 7488126 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9560. Min Act: -0.1695
Data Index: 2791766 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9475. Min Act: -0.1700
Data Index: 1553035 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9305. Min Act: -0.1697
Data Index: 7909825 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9305. Min Act: -0.1669
Data Index: 6637153 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9305. Min Act: -0.1689
Data Index: 7548416 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9135. Min Act: -0.1698
Data Index: 4870514 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9220. Min Act: -0.1700
Data Index: 1451966 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9305. Min Act: -0.1700
Data Index: 4350556 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9220. Min Act: -0.1699
Data Index: 6076825 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0068. Min Range: -2.0068
Max Act: 1.9220. Min Act: -0.1700
Data Index: 6312086 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19