Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3827 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1652. Min Range: -7.1652
Max Act: 7.1652. Min Act: -0.1700
Data Index: 3750925 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1652. Min Range: -7.1652
Max Act: 7.1027. Min Act: -0.1700
Data Index: 6222270 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1652. Min Range: -7.1652
Max Act: 7.1027. Min Act: -0.1700
Data Index: 2098619 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1652. Min Range: -7.1652
Max Act: 7.0714. Min Act: -0.1700
Data Index: 4002651 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.9777. Min Act: -0.1700
Data Index: 1706507 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.9152. Min Act: -0.1700
Data Index: 6678352 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.9152. Min Act: -0.1700
Data Index: 3385955 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.9152. Min Act: -0.1700
Data Index: 1150716 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.8527. Min Act: -0.1700
Data Index: 3197962 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.8527. Min Act: -0.1700
Data Index: 3501141 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.7277. Min Act: -0.1700
Data Index: 3366275 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.7277. Min Act: -0.1700
Data Index: 4753153 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.7277. Min Act: -0.1700
Data Index: 2522788 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.6964. Min Act: -0.1700
Data Index: 8368511 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.6964. Min Act: -0.1700
Data Index: 1062810 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.6964. Min Act: -0.1700
Data Index: 7474812 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.6652. Min Act: -0.1700
Data Index: 8251842 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.6652. Min Act: -0.1700
Data Index: 2224177 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.6652. Min Act: -0.1700
Data Index: 862587 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1652. Min Range: -7.1652
Max Act: 6.6339. Min Act: -0.1700
Data Index: 1014797 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19