Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1440 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0214. Min Range: -5.0214
Max Act: 5.0214. Min Act: -0.1700
Data Index: 5620688 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.9589. Min Act: -0.1700
Data Index: 8029417 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8964. Min Act: -0.1700
Data Index: 116945 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8964. Min Act: -0.1700
Data Index: 2427325 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8652. Min Act: -0.1700
Data Index: 3776844 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8964. Min Act: -0.1700
Data Index: 7415516 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8339. Min Act: -0.1700
Data Index: 2442916 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8027. Min Act: -0.1700
Data Index: 1336487 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7402. Min Act: -0.1700
Data Index: 2311433 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8027. Min Act: -0.1700
Data Index: 3773418 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.8027. Min Act: -0.1700
Data Index: 356180 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7714. Min Act: -0.1700
Data Index: 4179541 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7714. Min Act: -0.1700
Data Index: 6168010 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7089. Min Act: -0.1700
Data Index: 7700628 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7089. Min Act: -0.1700
Data Index: 2013917 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7089. Min Act: -0.1700
Data Index: 5332679 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7402. Min Act: -0.1700
Data Index: 4955135 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7089. Min Act: -0.1700
Data Index: 4592988 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7714. Min Act: -0.1700
Data Index: 7323741 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0214. Min Range: -5.0214
Max Act: 4.7402. Min Act: -0.1700
Data Index: 1014687 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19