Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6120 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.8860. Min Act: -0.1700
Data Index: 8584468 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.6673. Min Act: -0.1700
Data Index: 290173 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.2298. Min Act: -0.1700
Data Index: 2796034 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.1360. Min Act: -0.1700
Data Index: 8796524 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.1360. Min Act: -0.1700
Data Index: 4954329 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.0735. Min Act: -0.1700
Data Index: 5752467 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.0735. Min Act: -0.1700
Data Index: 8625320 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.0735. Min Act: -0.1700
Data Index: 313134 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.0423. Min Act: -0.1700
Data Index: 1609276 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.0423. Min Act: -0.1700
Data Index: 3266174 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8860. Min Range: -6.8860
Max Act: 6.0423. Min Act: -0.1700
Data Index: 5245152 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8860. Min Range: -6.8860
Max Act: 5.9798. Min Act: -0.1700
Data Index: 706365 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8860. Min Range: -6.8860
Max Act: 5.9485. Min Act: -0.1700
Data Index: 6208922 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8860. Min Range: -6.8860
Max Act: 5.9798. Min Act: -0.1700
Data Index: 659939 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8860. Min Range: -6.8860
Max Act: 5.9173. Min Act: -0.1700
Data Index: 8287632 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8860. Min Range: -6.8860
Max Act: 5.8860. Min Act: -0.1700
Data Index: 6361746 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8860. Min Range: -6.8860
Max Act: 5.8235. Min Act: -0.1700
Data Index: 3930642 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8860. Min Range: -6.8860
Max Act: 5.8235. Min Act: -0.1700
Data Index: 1096721 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8860. Min Range: -6.8860
Max Act: 5.8235. Min Act: -0.1700
Data Index: 453024 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8860. Min Range: -6.8860
Max Act: 5.8235. Min Act: -0.1700
Data Index: 8382100 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19