Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2452 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.8160. Min Act: -0.1700
Data Index: 7979497 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.7534. Min Act: -0.1700
Data Index: 1047161 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.7221. Min Act: -0.1700
Data Index: 6497014 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6908. Min Act: -0.1700
Data Index: 8486593 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 7547165 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.7221. Min Act: -0.1700
Data Index: 8226066 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 4200622 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 8249660 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 6825626 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 4432921 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6908. Min Act: -0.1700
Data Index: 4345970 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6283. Min Act: -0.1700
Data Index: 3404871 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 3021972 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 4522477 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 8667926 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 4557484 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6283. Min Act: -0.1700
Data Index: 3970072 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 4898664 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 8753745 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8160. Min Range: -3.8160
Max Act: 3.6595. Min Act: -0.1700
Data Index: 4641144 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19