Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5664 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.5432. Min Act: -0.1700
Data Index: 3220971 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.4807. Min Act: -0.1700
Data Index: 7051385 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.4182. Min Act: -0.1700
Data Index: 3055973 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.3557. Min Act: -0.1700
Data Index: 3690070 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.3557. Min Act: -0.1700
Data Index: 1599446 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.2932. Min Act: -0.1700
Data Index: 4453891 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.2932. Min Act: -0.1700
Data Index: 8394575 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.1057. Min Act: -0.1700
Data Index: 4813726 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.0432. Min Act: -0.1700
Data Index: 96173 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.1057. Min Act: -0.1700
Data Index: 8749158 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.1057. Min Act: -0.1700
Data Index: 1533939 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.0432. Min Act: -0.1700
Data Index: 4947683 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5432. Min Range: -10.5432
Max Act: 10.0432. Min Act: -0.1700
Data Index: 7581056 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5432. Min Range: -10.5432
Max Act: 9.9807. Min Act: -0.1700
Data Index: 6978205 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5432. Min Range: -10.5432
Max Act: 9.9807. Min Act: -0.1700
Data Index: 2864531 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5432. Min Range: -10.5432
Max Act: 9.9807. Min Act: -0.1700
Data Index: 4809296 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5432. Min Range: -10.5432
Max Act: 9.9807. Min Act: -0.1700
Data Index: 8128239 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5432. Min Range: -10.5432
Max Act: 9.9807. Min Act: -0.1700
Data Index: 4574887 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5432. Min Range: -10.5432
Max Act: 9.9182. Min Act: -0.1700
Data Index: 2647704 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5432. Min Range: -10.5432
Max Act: 9.9182. Min Act: -0.1700
Data Index: 601149 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19