Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1796 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2990. Min Range: -4.2990
Max Act: 4.2990. Min Act: -0.1700
Data Index: 2984087 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2990. Min Range: -4.2990
Max Act: 4.1740. Min Act: -0.1700
Data Index: 721066 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2990. Min Range: -4.2990
Max Act: 4.1115. Min Act: -0.1700
Data Index: 4046804 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2990. Min Range: -4.2990
Max Act: 4.0803. Min Act: -0.1700
Data Index: 2584526 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.9865. Min Act: -0.1700
Data Index: 1656081 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2990. Min Range: -4.2990
Max Act: 4.0490. Min Act: -0.1700
Data Index: 6625870 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2990. Min Range: -4.2990
Max Act: 4.0490. Min Act: -0.1700
Data Index: 4571699 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.9865. Min Act: -0.1700
Data Index: 2250507 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.9240. Min Act: -0.1700
Data Index: 2003649 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.8927. Min Act: -0.1700
Data Index: 93615 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.8301. Min Act: -0.1700
Data Index: 3431521 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.8458. Min Act: -0.1700
Data Index: 4387440 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.8301. Min Act: -0.1700
Data Index: 6801129 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.8301. Min Act: -0.1700
Data Index: 2447122 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.8301. Min Act: -0.1700
Data Index: 6054156 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.8145. Min Act: -0.1700
Data Index: 3324132 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.8145. Min Act: -0.1700
Data Index: 2738955 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.7989. Min Act: -0.1700
Data Index: 4966030 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.7832. Min Act: -0.1700
Data Index: 7303715 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2990. Min Range: -4.2990
Max Act: 3.7363. Min Act: -0.1700
Data Index: 4557804 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19