Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1181 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.3438. Min Act: -0.1700
Data Index: 7949460 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.3438. Min Act: -0.1700
Data Index: 7068714 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.3125. Min Act: -0.1700
Data Index: 8779306 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.2500. Min Act: -0.1700
Data Index: 6174378 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.2500. Min Act: -0.1700
Data Index: 490155 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1875. Min Act: -0.1700
Data Index: 2055723 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1562. Min Act: -0.1700
Data Index: 3716150 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1250. Min Act: -0.1700
Data Index: 6930688 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.1250. Min Act: -0.1700
Data Index: 6339015 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0937. Min Act: -0.1700
Data Index: 3131733 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0937. Min Act: -0.1700
Data Index: 7384227 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0937. Min Act: -0.1700
Data Index: 7490392 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0937. Min Act: -0.1700
Data Index: 2481222 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0937. Min Act: -0.1700
Data Index: 3742496 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0937. Min Act: -0.1700
Data Index: 7805660 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0937. Min Act: -0.1700
Data Index: 5356296 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0937. Min Act: -0.1700
Data Index: 1588336 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0937. Min Act: -0.1700
Data Index: 4324163 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0625. Min Act: -0.1700
Data Index: 1899918 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3438. Min Range: -4.3438
Max Act: 4.0000. Min Act: -0.1700
Data Index: 7201412 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19