Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5247 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.6077. Min Act: -0.1700
Data Index: 1275491 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.5764. Min Act: -0.1700
Data Index: 4353222 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.5139. Min Act: -0.1700
Data Index: 34168 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.4202. Min Act: -0.1700
Data Index: 3595966 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.4202. Min Act: -0.1700
Data Index: 8600129 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.4202. Min Act: -0.1700
Data Index: 1387371 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.3577. Min Act: -0.1700
Data Index: 2636445 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.3889. Min Act: -0.1700
Data Index: 6322065 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.3264. Min Act: -0.1700
Data Index: 7260466 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2952. Min Act: -0.1700
Data Index: 503897 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.3264. Min Act: -0.1700
Data Index: 6315516 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2327. Min Act: -0.1700
Data Index: 2234127 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2327. Min Act: -0.1700
Data Index: 238421 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2327. Min Act: -0.1700
Data Index: 8076597 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2639. Min Act: -0.1700
Data Index: 7659328 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2014. Min Act: -0.1700
Data Index: 821390 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2014. Min Act: -0.1700
Data Index: 1891595 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2014. Min Act: -0.1700
Data Index: 1353081 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.2327. Min Act: -0.1700
Data Index: 5269678 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6077. Min Range: -5.6077
Max Act: 5.1702. Min Act: -0.1700
Data Index: 2837262 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19