Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.5419. Min Act: -0.1700
Data Index: 8473781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.5419. Min Act: -0.1700
Data Index: 4377690 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4792. Min Act: -0.1700
Data Index: 328201 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.5105. Min Act: -0.1700
Data Index: 1140345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4792. Min Act: -0.1700
Data Index: 7732013 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4792. Min Act: -0.1700
Data Index: 2632846 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 3510344 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 7972119 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4165. Min Act: -0.1700
Data Index: 3471992 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4165. Min Act: -0.1700
Data Index: 7689039 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 7972124 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 261715 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 7972117 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 7057310 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 5859306 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 5614836 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 2707631 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 3579417 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 5362429 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5419. Min Range: -3.5419
Max Act: 3.4479. Min Act: -0.1700
Data Index: 480481 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19