Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1389 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5440. Min Range: -7.5440
Max Act: 7.5440. Min Act: -0.1700
Data Index: 6860640 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5440. Min Range: -7.5440
Max Act: 7.2315. Min Act: -0.1700
Data Index: 51310 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5440. Min Range: -7.5440
Max Act: 7.0753. Min Act: -0.1700
Data Index: 819377 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5440. Min Range: -7.5440
Max Act: 7.0440. Min Act: -0.1700
Data Index: 943235 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5440. Min Range: -7.5440
Max Act: 7.0440. Min Act: -0.1700
Data Index: 6236669 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.8253. Min Act: -0.1700
Data Index: 1885792 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.8565. Min Act: -0.1700
Data Index: 4909367 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.8253. Min Act: -0.1700
Data Index: 305917 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7940. Min Act: -0.1700
Data Index: 5436617 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7940. Min Act: -0.1700
Data Index: 4946928 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7940. Min Act: -0.1700
Data Index: 7588569 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7940. Min Act: -0.1700
Data Index: 5275544 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7940. Min Act: -0.1700
Data Index: 6121518 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7940. Min Act: -0.1700
Data Index: 5354752 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7315. Min Act: -0.1700
Data Index: 5739377 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7628. Min Act: -0.1700
Data Index: 815538 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7628. Min Act: -0.1700
Data Index: 3862778 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7628. Min Act: -0.1700
Data Index: 3761501 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7003. Min Act: -0.1700
Data Index: 649459 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5440. Min Range: -7.5440
Max Act: 6.7315. Min Act: -0.1700
Data Index: 3798562 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19