Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.8149. Min Act: -0.1700
Data Index: 3077395 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.8149. Min Act: -0.1700
Data Index: 8505032 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.7837. Min Act: -0.1700
Data Index: 1887850 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.7524. Min Act: -0.1700
Data Index: 3077396 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.7212. Min Act: -0.1700
Data Index: 6117424 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.6899. Min Act: -0.1700
Data Index: 495034 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.6899. Min Act: -0.1700
Data Index: 1799803 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.6587. Min Act: -0.1700
Data Index: 2948753 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.6587. Min Act: -0.1700
Data Index: 7073879 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.6587. Min Act: -0.1700
Data Index: 5772562 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5962. Min Act: -0.1700
Data Index: 2129046 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5962. Min Act: -0.1700
Data Index: 846418 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5649. Min Act: -0.1700
Data Index: 187721 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5649. Min Act: -0.1700
Data Index: 2174773 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5337. Min Act: -0.1700
Data Index: 846221 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5337. Min Act: -0.1700
Data Index: 4222418 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5337. Min Act: -0.1700
Data Index: 7410541 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5337. Min Act: -0.1700
Data Index: 821202 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5337. Min Act: -0.1700
Data Index: 5987533 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8149. Min Range: -6.8149
Max Act: 6.5337. Min Act: -0.1700
Data Index: 3377461 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19