Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2037 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.3142. Min Act: -0.1700
Data Index: 7722414 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.3142. Min Act: -0.1700
Data Index: 4356894 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2829. Min Act: -0.1700
Data Index: 4681709 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2829. Min Act: -0.1700
Data Index: 581181 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2829. Min Act: -0.1700
Data Index: 4181086 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2829. Min Act: -0.1700
Data Index: 1764611 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2517. Min Act: -0.1700
Data Index: 8810785 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2204. Min Act: -0.1700
Data Index: 2906002 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2204. Min Act: -0.1700
Data Index: 7634848 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2204. Min Act: -0.1700
Data Index: 681144 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2517. Min Act: -0.1700
Data Index: 1786244 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.2204. Min Act: -0.1700
Data Index: 6865467 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1892. Min Act: -0.1700
Data Index: 2628625 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1579. Min Act: -0.1700
Data Index: 709137 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1579. Min Act: -0.1700
Data Index: 1279183 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1579. Min Act: -0.1700
Data Index: 1145165 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1579. Min Act: -0.1700
Data Index: 3289009 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1267. Min Act: -0.1700
Data Index: 3138682 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1267. Min Act: -0.1700
Data Index: 4816356 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3142. Min Range: -4.3142
Max Act: 4.1267. Min Act: -0.1700
Data Index: 4511040 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19