Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4045 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.8196. Min Act: -0.1700
Data Index: 3814049 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.7414. Min Act: -0.1700
Data Index: 3558137 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.7102. Min Act: -0.1700
Data Index: 6777175 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5693. Min Act: -0.1700
Data Index: 2222696 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5850. Min Act: -0.1700
Data Index: 4567322 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5380. Min Act: -0.1700
Data Index: 7220520 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5224. Min Act: -0.1700
Data Index: 2704189 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5380. Min Act: -0.1700
Data Index: 3244710 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5224. Min Act: -0.1700
Data Index: 8198692 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5067. Min Act: -0.1700
Data Index: 6788171 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5067. Min Act: -0.1700
Data Index: 7979447 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5224. Min Act: -0.1700
Data Index: 6751521 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.4910. Min Act: -0.1700
Data Index: 5002297 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.5067. Min Act: -0.1700
Data Index: 4070375 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.4754. Min Act: -0.1700
Data Index: 4832070 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.4597. Min Act: -0.1700
Data Index: 8625703 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.4440. Min Act: -0.1700
Data Index: 7083944 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.4597. Min Act: -0.1700
Data Index: 7685000 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.4910. Min Act: -0.1700
Data Index: 1114636 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8196. Min Range: -3.8196
Max Act: 3.4284. Min Act: -0.1700
Data Index: 1271472 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19