Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.8215. Min Act: -0.1700
Data Index: 5044065 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.6964. Min Act: -0.1700
Data Index: 936009 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7276. Min Act: -0.1700
Data Index: 1079530 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.6494. Min Act: -0.1700
Data Index: 5212222 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.6651. Min Act: -0.1700
Data Index: 4627078 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.6338. Min Act: -0.1700
Data Index: 2666994 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.6181. Min Act: -0.1700
Data Index: 4940160 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.5868. Min Act: -0.1700
Data Index: 6641725 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.5399. Min Act: -0.1700
Data Index: 8581010 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.5399. Min Act: -0.1700
Data Index: 3758396 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.5399. Min Act: -0.1700
Data Index: 7754323 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.5555. Min Act: -0.1700
Data Index: 441394 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.4772. Min Act: -0.1700
Data Index: 720516 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.4929. Min Act: -0.1700
Data Index: 2487880 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.4615. Min Act: -0.1700
Data Index: 830966 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.4929. Min Act: -0.1700
Data Index: 2273972 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.4772. Min Act: -0.1700
Data Index: 956669 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.4772. Min Act: -0.1700
Data Index: 3021640 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.4145. Min Act: -0.1700
Data Index: 4301906 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.4615. Min Act: -0.1700
Data Index: 1851700 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19