Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.5781. Min Act: -0.1700
Data Index: 7248748 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.6093. Min Act: -0.1700
Data Index: 5969058 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.5156. Min Act: -0.1700
Data Index: 4933165 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.4218. Min Act: -0.1700
Data Index: 3822135 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.2343. Min Act: -0.1700
Data Index: 2096065 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.2343. Min Act: -0.1700
Data Index: 2012095 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.2343. Min Act: -0.1700
Data Index: 2481021 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.2343. Min Act: -0.1700
Data Index: 1489823 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.2343. Min Act: -0.1700
Data Index: 8695042 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.1718. Min Act: -0.1700
Data Index: 4391940 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.1718. Min Act: -0.1700
Data Index: 4991340 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.1093. Min Act: -0.1700
Data Index: 2342811 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.1406. Min Act: -0.1700
Data Index: 2128189 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.1093. Min Act: -0.1700
Data Index: 2256041 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.1093. Min Act: -0.1700
Data Index: 4414555 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.0468. Min Act: -0.1700
Data Index: 6949511 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.0468. Min Act: -0.1700
Data Index: 2017924 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.0468. Min Act: -0.1700
Data Index: 359071 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.0468. Min Act: -0.1700
Data Index: 5005834 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6093. Min Range: -6.6093
Max Act: 6.0156. Min Act: -0.1700
Data Index: 5437410 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19