Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1450 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.4973. Min Act: -0.1700
Data Index: 4411678 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.4348. Min Act: -0.1695
Data Index: 7341726 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.3723. Min Act: -0.1700
Data Index: 5076120 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.3723. Min Act: -0.1700
Data Index: 2511941 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.3723. Min Act: -0.1692
Data Index: 6867013 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.3723. Min Act: -0.1700
Data Index: 506495 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.3723. Min Act: -0.1700
Data Index: 5363825 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.3098. Min Act: -0.1700
Data Index: 8248426 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 7723807 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.1848. Min Act: -0.1700
Data Index: 8687660 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 2301896 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 8539826 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 1893396 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1695
Data Index: 8129731 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 7750744 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 1619013 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 2005608 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 7288113 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 3177184 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4973. Min Range: -7.4973
Max Act: 7.2473. Min Act: -0.1700
Data Index: 156447 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19