Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.5271. Min Act: -0.1700
Data Index: 4280328 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.5271. Min Act: -0.1700
Data Index: 4750319 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4801. Min Act: -0.1700
Data Index: 4009097 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4644. Min Act: -0.1700
Data Index: 254793 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4644. Min Act: -0.1700
Data Index: 2132378 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4331. Min Act: -0.1700
Data Index: 7023745 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4331. Min Act: -0.1700
Data Index: 1208795 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4331. Min Act: -0.1700
Data Index: 5796287 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4174. Min Act: -0.1700
Data Index: 8695799 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4174. Min Act: -0.1700
Data Index: 3149064 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4331. Min Act: -0.1700
Data Index: 2216223 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4174. Min Act: -0.1700
Data Index: 7014429 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4174. Min Act: -0.1700
Data Index: 4627510 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3860. Min Act: -0.1700
Data Index: 7797422 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4017. Min Act: -0.1700
Data Index: 3449996 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3704. Min Act: -0.1700
Data Index: 5200736 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3860. Min Act: -0.1700
Data Index: 7855505 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3860. Min Act: -0.1700
Data Index: 6091212 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3704. Min Act: -0.1700
Data Index: 7719277 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3860. Min Act: -0.1700
Data Index: 6487118 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19