Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1903 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.5968. Min Act: -0.1700
Data Index: 4898120 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.5655. Min Act: -0.1700
Data Index: 8359868 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.5343. Min Act: -0.1700
Data Index: 5185825 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.5343. Min Act: -0.1700
Data Index: 1931425 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.5030. Min Act: -0.1700
Data Index: 3260642 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.5030. Min Act: -0.1700
Data Index: 1219420 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.5030. Min Act: -0.1700
Data Index: 3240812 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4718. Min Act: -0.1700
Data Index: 5938860 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.5030. Min Act: -0.1700
Data Index: 5124798 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.5030. Min Act: -0.1700
Data Index: 7279815 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4718. Min Act: -0.1700
Data Index: 2976080 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4718. Min Act: -0.1700
Data Index: 8102500 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4718. Min Act: -0.1700
Data Index: 3430107 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4718. Min Act: -0.1700
Data Index: 6115159 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4718. Min Act: -0.1700
Data Index: 3833168 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4405. Min Act: -0.1700
Data Index: 120737 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4092. Min Act: -0.1700
Data Index: 4907905 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4092. Min Act: -0.1700
Data Index: 1759756 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4405. Min Act: -0.1700
Data Index: 822213 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5968. Min Range: -4.5968
Max Act: 4.4405. Min Act: -0.1700
Data Index: 1770797 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19