Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.9015. Min Act: -0.1698
Data Index: 156906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.8245. Min Act: -0.1670
Data Index: 3238774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.7815. Min Act: -0.1700
Data Index: 3967288 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.7642. Min Act: -0.1612
Data Index: 1917945 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.7123. Min Act: -0.1683
Data Index: 3260767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.7210. Min Act: -0.1700
Data Index: 5160318 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.7037. Min Act: -0.1686
Data Index: 1716982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6429. Min Act: -0.1700
Data Index: 1076600 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6429. Min Act: -0.1690
Data Index: 247172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6429. Min Act: -0.1700
Data Index: 7169594 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6516. Min Act: -0.1700
Data Index: 7303313 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6429. Min Act: -0.1700
Data Index: 6204726 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6341. Min Act: -0.1700
Data Index: 641336 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6254. Min Act: -0.1699
Data Index: 5998740 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6254. Min Act: -0.1699
Data Index: 755593 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.5993. Min Act: -0.1700
Data Index: 6945688 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6167. Min Act: -0.1698
Data Index: 4733092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6167. Min Act: -0.1699
Data Index: 8431805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.6080. Min Act: -0.1700
Data Index: 8832628 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9015. Min Range: -1.9015
Max Act: 1.5818. Min Act: -0.1700
Data Index: 1518059 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19