Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.7249. Min Act: -0.1700
Data Index: 8799802 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.3186. Min Act: -0.1700
Data Index: 3541898 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.1936. Min Act: -0.1700
Data Index: 76920 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.1624. Min Act: -0.1700
Data Index: 5874575 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.1311. Min Act: -0.1700
Data Index: 4383547 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.1311. Min Act: -0.1700
Data Index: 7154227 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.1311. Min Act: -0.1700
Data Index: 3311687 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0999. Min Act: -0.1700
Data Index: 3292444 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0999. Min Act: -0.1700
Data Index: 7669469 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0999. Min Act: -0.1700
Data Index: 4135317 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0373. Min Act: -0.1700
Data Index: 6241177 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0686. Min Act: -0.1700
Data Index: 6578523 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0686. Min Act: -0.1700
Data Index: 1090355 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7249. Min Range: -4.7249
Max Act: 4.0061. Min Act: -0.1700
Data Index: 6812703 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7249. Min Range: -4.7249
Max Act: 3.9748. Min Act: -0.1700
Data Index: 8355764 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7249. Min Range: -4.7249
Max Act: 3.9748. Min Act: -0.1700
Data Index: 1270651 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7249. Min Range: -4.7249
Max Act: 3.9748. Min Act: -0.1700
Data Index: 5203635 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7249. Min Range: -4.7249
Max Act: 3.9748. Min Act: -0.1700
Data Index: 1218519 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7249. Min Range: -4.7249
Max Act: 3.9748. Min Act: -0.1700
Data Index: 4855768 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7249. Min Range: -4.7249
Max Act: 3.9748. Min Act: -0.1700
Data Index: 3254379 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19