Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.9442. Min Act: -0.1700
Data Index: 3055367 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.9130. Min Act: -0.1700
Data Index: 6543846 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.9442. Min Act: -0.1700
Data Index: 8342697 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.8505. Min Act: -0.1700
Data Index: 2974349 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.8192. Min Act: -0.1700
Data Index: 5782031 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.7880. Min Act: -0.1700
Data Index: 1019829 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.6942. Min Act: -0.1700
Data Index: 4167183 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.6630. Min Act: -0.1700
Data Index: 3095781 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.6942. Min Act: -0.1700
Data Index: 1633332 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.6942. Min Act: -0.1700
Data Index: 5367132 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.6942. Min Act: -0.1700
Data Index: 4720583 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.6630. Min Act: -0.1700
Data Index: 96794 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.6630. Min Act: -0.1700
Data Index: 6647665 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.6317. Min Act: -0.1700
Data Index: 6952885 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.6005. Min Act: -0.1700
Data Index: 6692210 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.5380. Min Act: -0.1700
Data Index: 96791 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.5380. Min Act: -0.1700
Data Index: 7729344 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.5380. Min Act: -0.1700
Data Index: 3486929 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.5692. Min Act: -0.1700
Data Index: 6317494 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9442. Min Range: -5.9442
Max Act: 5.5067. Min Act: -0.1700
Data Index: 7911284 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19