Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4051 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3312. Min Range: -5.3312
Max Act: 5.3312. Min Act: -0.1700
Data Index: 2071660 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3312. Min Range: -5.3312
Max Act: 5.0812. Min Act: -0.1700
Data Index: 4353132 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3312. Min Range: -5.3312
Max Act: 5.0187. Min Act: -0.1700
Data Index: 4557411 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.9562. Min Act: -0.1700
Data Index: 7276719 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.8937. Min Act: -0.1700
Data Index: 5993730 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.8624. Min Act: -0.1700
Data Index: 3592239 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.8624. Min Act: -0.1700
Data Index: 7335483 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.8312. Min Act: -0.1700
Data Index: 6018912 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.8312. Min Act: -0.1700
Data Index: 8725924 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7999. Min Act: -0.1700
Data Index: 627105 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7999. Min Act: -0.1700
Data Index: 982261 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7687. Min Act: -0.1700
Data Index: 1941642 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7999. Min Act: -0.1700
Data Index: 328884 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7687. Min Act: -0.1700
Data Index: 443750 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7687. Min Act: -0.1700
Data Index: 191362 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7374. Min Act: -0.1700
Data Index: 8419914 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7374. Min Act: -0.1700
Data Index: 6304375 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7062. Min Act: -0.1700
Data Index: 6679414 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7062. Min Act: -0.1700
Data Index: 3176420 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3312. Min Range: -5.3312
Max Act: 4.7062. Min Act: -0.1700
Data Index: 181373 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19