Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.7628. Min Act: -0.1700
Data Index: 921498 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.4654. Min Act: -0.1700
Data Index: 422787 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.4184. Min Act: -0.1700
Data Index: 2371502 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3870. Min Act: -0.1700
Data Index: 1049576 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3556. Min Act: -0.1700
Data Index: 6908865 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3713. Min Act: -0.1700
Data Index: 3550971 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3713. Min Act: -0.1700
Data Index: 2161675 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3400. Min Act: -0.1700
Data Index: 3714694 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3400. Min Act: -0.1700
Data Index: 5918638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3243. Min Act: -0.1700
Data Index: 1256063 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3400. Min Act: -0.1700
Data Index: 1315062 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3086. Min Act: -0.1700
Data Index: 6630639 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3086. Min Act: -0.1700
Data Index: 1582180 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.3086. Min Act: -0.1700
Data Index: 5054869 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.2929. Min Act: -0.1700
Data Index: 2131028 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.2772. Min Act: -0.1700
Data Index: 6351315 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.2929. Min Act: -0.1700
Data Index: 4589048 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.2772. Min Act: -0.1700
Data Index: 5915615 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.2772. Min Act: -0.1700
Data Index: 7468448 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7628. Min Range: -3.7628
Max Act: 3.2772. Min Act: -0.1700
Data Index: 5313674 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19