Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2941. Min Range: -8.2941
Max Act: 8.2941. Min Act: -0.1700
Data Index: 1175927 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2941. Min Range: -8.2941
Max Act: 8.2941. Min Act: -0.1700
Data Index: 1948621 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2941. Min Range: -8.2941
Max Act: 8.1691. Min Act: -0.1700
Data Index: 2588572 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2941. Min Range: -8.2941
Max Act: 8.1066. Min Act: -0.1700
Data Index: 7691644 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2941. Min Range: -8.2941
Max Act: 8.0129. Min Act: -0.1700
Data Index: 5781478 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2941. Min Range: -8.2941
Max Act: 8.0129. Min Act: -0.1700
Data Index: 8619807 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.9816. Min Act: -0.1700
Data Index: 2249767 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.7941. Min Act: -0.1700
Data Index: 53048 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.7941. Min Act: -0.1700
Data Index: 7247262 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.7629. Min Act: -0.1700
Data Index: 8619811 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.7316. Min Act: -0.1700
Data Index: 274692 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.6066. Min Act: -0.1700
Data Index: 53047 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.6066. Min Act: -0.1700
Data Index: 3672213 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.5129. Min Act: -0.1700
Data Index: 1175938 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.5441. Min Act: -0.1700
Data Index: 7846586 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.5129. Min Act: -0.1700
Data Index: 7911788 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.4816. Min Act: -0.1700
Data Index: 5019798 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.5129. Min Act: -0.1700
Data Index: 3697831 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.4816. Min Act: -0.1700
Data Index: 7116144 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2941. Min Range: -8.2941
Max Act: 7.5129. Min Act: -0.1700
Data Index: 4501732 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19