Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 63 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.8948. Min Act: -0.1700
Data Index: 994671 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.8323. Min Act: -0.1700
Data Index: 6159108 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.6760. Min Act: -0.1700
Data Index: 3325379 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.5510. Min Act: -0.1700
Data Index: 8524160 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.5510. Min Act: -0.1700
Data Index: 5003276 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.5823. Min Act: -0.1700
Data Index: 3047425 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.4885. Min Act: -0.1700
Data Index: 1493501 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.5198. Min Act: -0.1700
Data Index: 2230677 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.4885. Min Act: -0.1700
Data Index: 2460288 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.4573. Min Act: -0.1700
Data Index: 3311322 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.4885. Min Act: -0.1700
Data Index: 3031572 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.4573. Min Act: -0.1700
Data Index: 5474304 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.4260. Min Act: -0.1700
Data Index: 8169435 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 5835121 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 4431975 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 5089769 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 7480982 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.4260. Min Act: -0.1700
Data Index: 7751554 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 1424049 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8948. Min Range: -5.8948
Max Act: 5.3948. Min Act: -0.1700
Data Index: 6079789 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19