Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 273 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9926. Min Range: -8.9926
Max Act: 8.9926. Min Act: -0.1700
Data Index: 2372552 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9926. Min Range: -8.9926
Max Act: 8.8051. Min Act: -0.1700
Data Index: 8783022 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9926. Min Range: -8.9926
Max Act: 8.5551. Min Act: -0.1700
Data Index: 6804937 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9926. Min Range: -8.9926
Max Act: 8.5551. Min Act: -0.1700
Data Index: 5715413 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9926. Min Range: -8.9926
Max Act: 8.2426. Min Act: -0.1700
Data Index: 5948741 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9926. Min Range: -8.9926
Max Act: 8.0238. Min Act: -0.1700
Data Index: 6849283 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.9926. Min Act: -0.1700
Data Index: 4250906 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.9926. Min Act: -0.1700
Data Index: 4363579 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.9613. Min Act: -0.1700
Data Index: 205631 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.9613. Min Act: -0.1700
Data Index: 7009930 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.8988. Min Act: -0.1700
Data Index: 5489263 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9926. Min Range: -8.9926
Max Act: 8.0238. Min Act: -0.1700
Data Index: 7013905 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.8988. Min Act: -0.1700
Data Index: 1811954 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.8988. Min Act: -0.1700
Data Index: 2811007 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.7738. Min Act: -0.1700
Data Index: 5175241 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.8051. Min Act: -0.1700
Data Index: 3093724 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.7738. Min Act: -0.1700
Data Index: 3631251 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.8051. Min Act: -0.1700
Data Index: 6783455 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.8051. Min Act: -0.1700
Data Index: 6727758 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9926. Min Range: -8.9926
Max Act: 7.8051. Min Act: -0.1700
Data Index: 6597124 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19