Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1401 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.6511. Min Act: -0.1700
Data Index: 3761927 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.6198. Min Act: -0.1700
Data Index: 2981328 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.6041. Min Act: -0.1700
Data Index: 8374136 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.6041. Min Act: -0.1700
Data Index: 8710437 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5728. Min Act: -0.1700
Data Index: 3221661 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5728. Min Act: -0.1700
Data Index: 3374849 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5728. Min Act: -0.1700
Data Index: 3575485 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5572. Min Act: -0.1700
Data Index: 4114552 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5728. Min Act: -0.1700
Data Index: 1584211 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5572. Min Act: -0.1700
Data Index: 5916456 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5728. Min Act: -0.1700
Data Index: 6246132 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5102. Min Act: -0.1700
Data Index: 7692988 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5258. Min Act: -0.1700
Data Index: 7988138 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5258. Min Act: -0.1700
Data Index: 2528235 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5728. Min Act: -0.1700
Data Index: 6868684 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.4945. Min Act: -0.1700
Data Index: 915268 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5258. Min Act: -0.1700
Data Index: 796760 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5258. Min Act: -0.1700
Data Index: 3616319 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5572. Min Act: -0.1700
Data Index: 1280719 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6511. Min Range: -3.6511
Max Act: 3.5102. Min Act: -0.1700
Data Index: 5413088 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19