Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2951 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.3141. Min Act: -0.1698
Data Index: 4710572 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1666
Data Index: 453976 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2611. Min Act: -0.1700
Data Index: 1138885 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2611. Min Act: -0.1660
Data Index: 7131439 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2611. Min Act: -0.1700
Data Index: 2667384 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1651
Data Index: 767656 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1697
Data Index: 2144403 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1686
Data Index: 725136 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1700
Data Index: 783291 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1699
Data Index: 1257041 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1700
Data Index: 743296 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1700
Data Index: 3447271 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1695
Data Index: 4789049 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1700
Data Index: 8718084 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2259. Min Act: -0.1696
Data Index: 57310 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2259. Min Act: -0.1693
Data Index: 6857852 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2259. Min Act: -0.1700
Data Index: 6368662 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2435. Min Act: -0.1698
Data Index: 5854484 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2259. Min Act: -0.1688
Data Index: 7231150 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3141. Min Range: -1.3141
Max Act: 1.2259. Min Act: -0.1693
Data Index: 4867088 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19