Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5876 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.4013. Min Act: -0.1700
Data Index: 4909545 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.3701. Min Act: -0.1700
Data Index: 373993 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2763. Min Act: -0.1700
Data Index: 831943 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2763. Min Act: -0.1700
Data Index: 2388335 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2763. Min Act: -0.1700
Data Index: 902524 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2451. Min Act: -0.1700
Data Index: 482858 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2138. Min Act: -0.1700
Data Index: 2377845 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2138. Min Act: -0.1700
Data Index: 1250314 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1826. Min Act: -0.1700
Data Index: 8483891 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2138. Min Act: -0.1700
Data Index: 8228578 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1513. Min Act: -0.1700
Data Index: 6987365 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1513. Min Act: -0.1700
Data Index: 6151002 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1513. Min Act: -0.1700
Data Index: 8365607 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1201. Min Act: -0.1700
Data Index: 8074567 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1201. Min Act: -0.1700
Data Index: 544649 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.0888. Min Act: -0.1700
Data Index: 4572737 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1201. Min Act: -0.1700
Data Index: 2233793 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1201. Min Act: -0.1700
Data Index: 7171219 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.0888. Min Act: -0.1700
Data Index: 4542339 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.0888. Min Act: -0.1700
Data Index: 7881150 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19