Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7664. Min Range: -8.7664
Max Act: 8.7664. Min Act: -0.1700
Data Index: 3116995 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7664. Min Range: -8.7664
Max Act: 8.1414. Min Act: -0.1700
Data Index: 110074 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7664. Min Range: -8.7664
Max Act: 8.0164. Min Act: -0.1700
Data Index: 5227207 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7664. Min Range: -8.7664
Max Act: 8.0164. Min Act: -0.1700
Data Index: 1291589 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.9539. Min Act: -0.1700
Data Index: 4811121 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.8289. Min Act: -0.1700
Data Index: 912684 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.8289. Min Act: -0.1700
Data Index: 6990145 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.7664. Min Act: -0.1700
Data Index: 5328654 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.7664. Min Act: -0.1700
Data Index: 1572137 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.7664. Min Act: -0.1700
Data Index: 1261061 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.7039. Min Act: -0.1700
Data Index: 1779175 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.7664. Min Act: -0.1700
Data Index: 6857771 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.7039. Min Act: -0.1700
Data Index: 7890530 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.7039. Min Act: -0.1700
Data Index: 4235849 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.6727. Min Act: -0.1700
Data Index: 2393769 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.7039. Min Act: -0.1700
Data Index: 941973 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.7039. Min Act: -0.1700
Data Index: 7748613 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.6727. Min Act: -0.1700
Data Index: 7436344 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.6727. Min Act: -0.1700
Data Index: 7083351 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7664. Min Range: -8.7664
Max Act: 7.6414. Min Act: -0.1700
Data Index: 415106 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19