Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.2697. Min Act: -0.1700
Data Index: 8090713 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.0651. Min Act: -0.1700
Data Index: 356652 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.1911. Min Act: -0.1700
Data Index: 6515456 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.1439. Min Act: -0.1700
Data Index: 4131633 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.0809. Min Act: -0.1700
Data Index: 3592813 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.0335. Min Act: -0.1700
Data Index: 1611399 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.0493. Min Act: -0.1700
Data Index: 160243 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.0335. Min Act: -0.1700
Data Index: 8381227 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.0177. Min Act: -0.1700
Data Index: 8607525 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.0335. Min Act: -0.1700
Data Index: 3737131 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2697. Min Range: -3.2697
Max Act: 2.9545. Min Act: -0.1700
Data Index: 6084236 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2697. Min Range: -3.2697
Max Act: 3.0019. Min Act: -0.1700
Data Index: 2323242 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2697. Min Range: -3.2697
Max Act: 2.9861. Min Act: -0.1700
Data Index: 61664 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2697. Min Range: -3.2697
Max Act: 2.9861. Min Act: -0.1700
Data Index: 1728018 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2697. Min Range: -3.2697
Max Act: 2.9703. Min Act: -0.1700
Data Index: 5226269 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2697. Min Range: -3.2697
Max Act: 2.9703. Min Act: -0.1700
Data Index: 6758719 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2697. Min Range: -3.2697
Max Act: 2.9545. Min Act: -0.1700
Data Index: 3632222 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2697. Min Range: -3.2697
Max Act: 2.9703. Min Act: -0.1700
Data Index: 1961128 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2697. Min Range: -3.2697
Max Act: 2.9387. Min Act: -0.1700
Data Index: 7932069 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2697. Min Range: -3.2697
Max Act: 2.9861. Min Act: -0.1700
Data Index: 3675686 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19