Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1226 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.3880. Min Act: -0.1700
Data Index: 6576294 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.3252. Min Act: -0.1700
Data Index: 860783 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.2153. Min Act: -0.1700
Data Index: 7450468 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1681. Min Act: -0.1700
Data Index: 3272011 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1681. Min Act: -0.1700
Data Index: 4790800 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1523. Min Act: -0.1700
Data Index: 4601153 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1523. Min Act: -0.1700
Data Index: 7250959 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1051. Min Act: -0.1700
Data Index: 6526218 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0736. Min Act: -0.1700
Data Index: 6533243 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0893. Min Act: -0.1700
Data Index: 2838392 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0893. Min Act: -0.1700
Data Index: 438372 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0893. Min Act: -0.1700
Data Index: 2035707 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0893. Min Act: -0.1700
Data Index: 2431703 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0893. Min Act: -0.1700
Data Index: 4177708 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0893. Min Act: -0.1700
Data Index: 7310648 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0893. Min Act: -0.1700
Data Index: 3087441 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0736. Min Act: -0.1700
Data Index: 2093188 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.1051. Min Act: -0.1700
Data Index: 4527193 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0736. Min Act: -0.1700
Data Index: 5132164 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3880. Min Range: -3.3880
Max Act: 3.0578. Min Act: -0.1700
Data Index: 2421793 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19