Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.9650. Min Act: -0.1700
Data Index: 62275 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.8400. Min Act: -0.1700
Data Index: 8692765 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7931. Min Act: -0.1700
Data Index: 1931359 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7931. Min Act: -0.1700
Data Index: 665136 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7462. Min Act: -0.1700
Data Index: 4683248 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7774. Min Act: -0.1700
Data Index: 1103691 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7774. Min Act: -0.1700
Data Index: 8817451 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7462. Min Act: -0.1700
Data Index: 6337022 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7305. Min Act: -0.1700
Data Index: 8781632 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7305. Min Act: -0.1700
Data Index: 7778091 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7462. Min Act: -0.1700
Data Index: 2623227 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7305. Min Act: -0.1700
Data Index: 5298090 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7305. Min Act: -0.1700
Data Index: 5260806 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7305. Min Act: -0.1700
Data Index: 6623596 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7462. Min Act: -0.1700
Data Index: 2028840 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.6836. Min Act: -0.1700
Data Index: 6323377 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7149. Min Act: -0.1700
Data Index: 4279975 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.6992. Min Act: -0.1700
Data Index: 5135497 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7305. Min Act: -0.1700
Data Index: 6680883 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9650. Min Range: -3.9650
Max Act: 3.7149. Min Act: -0.1700
Data Index: 7678429 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19