Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.9991. Min Act: -0.1700
Data Index: 5094362 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.9678. Min Act: -0.1700
Data Index: 7199487 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.9678. Min Act: -0.1700
Data Index: 410659 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.9053. Min Act: -0.1700
Data Index: 1754766 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.9366. Min Act: -0.1700
Data Index: 7460731 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.8741. Min Act: -0.1700
Data Index: 126078 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.8428. Min Act: -0.1700
Data Index: 5883612 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.8428. Min Act: -0.1700
Data Index: 2947506 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.7803. Min Act: -0.1700
Data Index: 8345296 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.7803. Min Act: -0.1700
Data Index: 507467 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.7803. Min Act: -0.1700
Data Index: 7404516 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.7803. Min Act: -0.1700
Data Index: 5335759 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.7803. Min Act: -0.1700
Data Index: 4290359 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.7178. Min Act: -0.1700
Data Index: 7975723 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.6866. Min Act: -0.1700
Data Index: 1670273 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.6866. Min Act: -0.1700
Data Index: 3293693 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.6866. Min Act: -0.1700
Data Index: 5025546 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.7178. Min Act: -0.1700
Data Index: 955675 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.6866. Min Act: -0.1700
Data Index: 4098006 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9991. Min Range: -6.9991
Max Act: 6.6866. Min Act: -0.1700
Data Index: 2591662 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19