Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8920. Min Act: -0.1700
Data Index: 40857 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8920. Min Act: -0.1700
Data Index: 23338 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 7056993 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 5791449 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 1082193 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8295. Min Act: -0.1700
Data Index: 3247353 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 8716406 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 2929738 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 2854347 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8295. Min Act: -0.1700
Data Index: 7705615 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 7531616 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 2225530 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 1895860 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8607. Min Act: -0.1700
Data Index: 1261805 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8295. Min Act: -0.1700
Data Index: 3002954 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8295. Min Act: -0.1700
Data Index: 1041136 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8295. Min Act: -0.1700
Data Index: 3324444 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8295. Min Act: -0.1700
Data Index: 5022962 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8295. Min Act: -0.1700
Data Index: 5180519 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8920. Min Range: -3.8920
Max Act: 3.8295. Min Act: -0.1700
Data Index: 5495030 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19