Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.9736. Min Act: -0.1700
Data Index: 701050 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.9580. Min Act: -0.1700
Data Index: 3611576 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.9424. Min Act: -0.1700
Data Index: 2013101 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.9111. Min Act: -0.1700
Data Index: 646312 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.9111. Min Act: -0.1700
Data Index: 4263099 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8955. Min Act: -0.1700
Data Index: 6958364 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8955. Min Act: -0.1700
Data Index: 1125980 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8642. Min Act: -0.1700
Data Index: 4227975 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.9111. Min Act: -0.1700
Data Index: 460353 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8798. Min Act: -0.1700
Data Index: 805557 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8798. Min Act: -0.1700
Data Index: 204473 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8798. Min Act: -0.1700
Data Index: 1906812 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8798. Min Act: -0.1700
Data Index: 3815170 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8798. Min Act: -0.1700
Data Index: 2390530 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8798. Min Act: -0.1700
Data Index: 444916 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8486. Min Act: -0.1700
Data Index: 4349350 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8642. Min Act: -0.1700
Data Index: 1946370 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8486. Min Act: -0.1700
Data Index: 4918920 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8642. Min Act: -0.1700
Data Index: 2816586 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9736. Min Range: -3.9736
Max Act: 3.8642. Min Act: -0.1700
Data Index: 1177675 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19