Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0255. Min Range: -2.0255
Max Act: 2.0255. Min Act: -0.1700
Data Index: 2507350 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9918. Min Act: -0.1700
Data Index: 4604512 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9918. Min Act: -0.1700
Data Index: 7898981 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9918. Min Act: -0.1700
Data Index: 4109754 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9918. Min Act: -0.1700
Data Index: 609383 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9748. Min Act: -0.1700
Data Index: 2949316 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9748. Min Act: -0.1700
Data Index: 6688040 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9748. Min Act: -0.1700
Data Index: 756061 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9748. Min Act: -0.1700
Data Index: 3489034 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9579. Min Act: -0.1700
Data Index: 1396869 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9748. Min Act: -0.1700
Data Index: 2253202 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9748. Min Act: -0.1700
Data Index: 4304120 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9579. Min Act: -0.1700
Data Index: 2107701 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9409. Min Act: -0.1700
Data Index: 990576 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9239. Min Act: -0.1700
Data Index: 3105456 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9579. Min Act: -0.1700
Data Index: 5920910 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9409. Min Act: -0.1700
Data Index: 3662227 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9239. Min Act: -0.1700
Data Index: 3101683 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9239. Min Act: -0.1700
Data Index: 1569991 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0255. Min Range: -2.0255
Max Act: 1.9409. Min Act: -0.1700
Data Index: 5294541 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19