Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.7195. Min Act: -0.1700
Data Index: 5954182 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.5945. Min Act: -0.1700
Data Index: 469827 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.5945. Min Act: -0.1700
Data Index: 7636985 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.5320. Min Act: -0.1700
Data Index: 8666832 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.5320. Min Act: -0.1700
Data Index: 7522156 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4695. Min Act: -0.1700
Data Index: 7480393 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4695. Min Act: -0.1700
Data Index: 3062481 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4695. Min Act: -0.1700
Data Index: 4096434 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4695. Min Act: -0.1700
Data Index: 7209319 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4382. Min Act: -0.1700
Data Index: 627270 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4070. Min Act: -0.1700
Data Index: 2697397 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4382. Min Act: -0.1700
Data Index: 837023 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4070. Min Act: -0.1700
Data Index: 4366961 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4382. Min Act: -0.1700
Data Index: 5372316 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4070. Min Act: -0.1700
Data Index: 4934426 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.3757. Min Act: -0.1700
Data Index: 5653426 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4070. Min Act: -0.1700
Data Index: 6278158 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4070. Min Act: -0.1700
Data Index: 2500775 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4070. Min Act: -0.1700
Data Index: 2475170 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7195. Min Range: -4.7195
Max Act: 4.4070. Min Act: -0.1700
Data Index: 6403236 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19