Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3127 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3180. Min Range: -5.3180
Max Act: 5.3180. Min Act: -0.1700
Data Index: 7758066 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3180. Min Range: -5.3180
Max Act: 5.0368. Min Act: -0.1700
Data Index: 8770288 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.8180. Min Act: -0.1700
Data Index: 7845321 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.8180. Min Act: -0.1700
Data Index: 4160930 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.8180. Min Act: -0.1700
Data Index: 7738275 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.7555. Min Act: -0.1700
Data Index: 6815806 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.7555. Min Act: -0.1700
Data Index: 1489039 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.7243. Min Act: -0.1700
Data Index: 424669 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.7243. Min Act: -0.1700
Data Index: 14888 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.6618. Min Act: -0.1700
Data Index: 318796 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.6930. Min Act: -0.1700
Data Index: 3144583 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.6618. Min Act: -0.1700
Data Index: 1118896 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.6618. Min Act: -0.1700
Data Index: 5319482 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.5993. Min Act: -0.1700
Data Index: 5797717 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.5993. Min Act: -0.1700
Data Index: 755336 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.5993. Min Act: -0.1700
Data Index: 6650325 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.5993. Min Act: -0.1700
Data Index: 6016489 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.5680. Min Act: -0.1700
Data Index: 1182012 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.5680. Min Act: -0.1700
Data Index: 6672024 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3180. Min Range: -5.3180
Max Act: 4.5680. Min Act: -0.1700
Data Index: 3860562 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19