Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.8888. Min Range: -10.8888
Max Act: 10.8888. Min Act: -0.1700
Data Index: 6745723 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8888. Min Range: -10.8888
Max Act: 10.7013. Min Act: -0.1700
Data Index: 1445384 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8888. Min Range: -10.8888
Max Act: 10.4513. Min Act: -0.1700
Data Index: 8076420 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8888. Min Range: -10.8888
Max Act: 10.2638. Min Act: -0.1700
Data Index: 7793752 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8888. Min Range: -10.8888
Max Act: 10.0763. Min Act: -0.1700
Data Index: 3409662 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.9513. Min Act: -0.1700
Data Index: 4099437 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8888. Min Range: -10.8888
Max Act: 10.0138. Min Act: -0.1700
Data Index: 5961100 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.8888. Min Act: -0.1699
Data Index: 7533181 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.8888. Min Act: -0.1700
Data Index: 6263723 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.8888. Min Act: -0.1700
Data Index: 6887698 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.8888. Min Act: -0.1700
Data Index: 7988019 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.7638. Min Act: -0.1700
Data Index: 153652 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.8263. Min Act: -0.1700
Data Index: 6782690 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.7638. Min Act: -0.1700
Data Index: 5815028 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.8263. Min Act: -0.1700
Data Index: 6329219 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.7638. Min Act: -0.1700
Data Index: 2231195 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.7638. Min Act: -0.1700
Data Index: 6971680 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.7013. Min Act: -0.1700
Data Index: 328297 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.7013. Min Act: -0.1700
Data Index: 356323 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8888. Min Range: -10.8888
Max Act: 9.6388. Min Act: -0.1700
Data Index: 4108042 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19