Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.8968. Min Act: -0.1700
Data Index: 4696845 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.8968. Min Act: -0.1700
Data Index: 3212988 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.8030. Min Act: -0.1700
Data Index: 2295916 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.8030. Min Act: -0.1700
Data Index: 5047176 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.8030. Min Act: -0.1700
Data Index: 8046067 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.7718. Min Act: -0.1700
Data Index: 7098186 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.7405. Min Act: -0.1700
Data Index: 7438123 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6780. Min Act: -0.1700
Data Index: 5594620 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.7093. Min Act: -0.1700
Data Index: 4572102 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.7093. Min Act: -0.1700
Data Index: 7923210 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6780. Min Act: -0.1700
Data Index: 4613674 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6780. Min Act: -0.1700
Data Index: 5740626 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6468. Min Act: -0.1700
Data Index: 4890086 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6468. Min Act: -0.1700
Data Index: 5882884 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6468. Min Act: -0.1700
Data Index: 1701312 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6155. Min Act: -0.1700
Data Index: 7264453 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5530. Min Act: -0.1700
Data Index: 6185222 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5843. Min Act: -0.1700
Data Index: 2658118 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5843. Min Act: -0.1700
Data Index: 6038745 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5843. Min Act: -0.1700
Data Index: 6099014 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19