Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1024 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0072. Min Range: -4.0072
Max Act: 4.0072. Min Act: -0.1700
Data Index: 4245637 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.9760. Min Act: -0.1700
Data Index: 4976151 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.9447. Min Act: -0.1700
Data Index: 3282838 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.9447. Min Act: -0.1700
Data Index: 8465089 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8822. Min Act: -0.1700
Data Index: 123243 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.9447. Min Act: -0.1700
Data Index: 4795093 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8822. Min Act: -0.1700
Data Index: 4839262 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8509. Min Act: -0.1700
Data Index: 5654293 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8822. Min Act: -0.1700
Data Index: 987884 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8509. Min Act: -0.1700
Data Index: 5177771 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8822. Min Act: -0.1700
Data Index: 5709562 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8822. Min Act: -0.1700
Data Index: 4306112 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8509. Min Act: -0.1700
Data Index: 7811187 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8196. Min Act: -0.1700
Data Index: 4028235 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8509. Min Act: -0.1700
Data Index: 6065377 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8822. Min Act: -0.1700
Data Index: 8638554 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8509. Min Act: -0.1700
Data Index: 5770498 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8509. Min Act: -0.1700
Data Index: 6548746 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8196. Min Act: -0.1700
Data Index: 4155161 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0072. Min Range: -4.0072
Max Act: 3.8196. Min Act: -0.1700
Data Index: 3373629 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19