Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.5071. Min Act: -0.1700
Data Index: 545527 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.5071. Min Act: -0.1700
Data Index: 2493123 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.5071. Min Act: -0.1700
Data Index: 3417121 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4909. Min Act: -0.1700
Data Index: 2895122 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4747. Min Act: -0.1700
Data Index: 7788365 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4909. Min Act: -0.1700
Data Index: 4893395 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4747. Min Act: -0.1700
Data Index: 8640065 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4747. Min Act: -0.1700
Data Index: 2493122 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4747. Min Act: -0.1700
Data Index: 7075769 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4584. Min Act: -0.1700
Data Index: 2493120 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4422. Min Act: -0.1700
Data Index: 3259708 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4422. Min Act: -0.1700
Data Index: 6296401 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4422. Min Act: -0.1700
Data Index: 6287134 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4584. Min Act: -0.1700
Data Index: 607553 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4259. Min Act: -0.1700
Data Index: 3580988 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4259. Min Act: -0.1700
Data Index: 502226 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4259. Min Act: -0.1700
Data Index: 3924458 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4259. Min Act: -0.1700
Data Index: 2493117 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.3933. Min Act: -0.1700
Data Index: 7930859 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5071. Min Range: -2.5071
Max Act: 2.4096. Min Act: -0.1700
Data Index: 1874915 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19