Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.5094. Min Act: -0.1700
Data Index: 5804975 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.5094. Min Act: -0.1700
Data Index: 2159003 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.4781. Min Act: -0.1700
Data Index: 1757053 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.3219. Min Act: -0.1700
Data Index: 1103315 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2906. Min Act: -0.1700
Data Index: 5492792 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2906. Min Act: -0.1700
Data Index: 2706136 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2906. Min Act: -0.1700
Data Index: 8354604 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2594. Min Act: -0.1700
Data Index: 6458894 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2594. Min Act: -0.1700
Data Index: 878671 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2594. Min Act: -0.1700
Data Index: 748800 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2594. Min Act: -0.1700
Data Index: 1382752 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2594. Min Act: -0.1700
Data Index: 7084306 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2281. Min Act: -0.1700
Data Index: 3692987 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.2281. Min Act: -0.1700
Data Index: 4020590 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.1969. Min Act: -0.1700
Data Index: 3332698 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.1656. Min Act: -0.1700
Data Index: 1648057 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.1344. Min Act: -0.1700
Data Index: 4226314 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.1344. Min Act: -0.1700
Data Index: 2555627 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.0719. Min Act: -0.1700
Data Index: 1566600 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5094. Min Range: -5.5094
Max Act: 5.1031. Min Act: -0.1700
Data Index: 1851014 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19