Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5692 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.7084. Min Act: -0.1700
Data Index: 6802268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.7084. Min Act: -0.1700
Data Index: 5733581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1692
Data Index: 297662 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1697
Data Index: 293709 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1685
Data Index: 284814 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.5834. Min Act: -0.1687
Data Index: 255627 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1700
Data Index: 254846 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1700
Data Index: 230174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1697
Data Index: 222351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1698
Data Index: 217332 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1687
Data Index: 206715 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1699
Data Index: 174310 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1700
Data Index: 152386 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1698
Data Index: 104437 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1700
Data Index: 84092 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1700
Data Index: 82371 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1700
Data Index: 57108 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1697
Data Index: 11651 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1699
Data Index: 46752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7084. Min Range: -8.7084
Max Act: 8.6459. Min Act: -0.1700
Data Index: 36603 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19