Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2399 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.6017. Min Act: -0.1700
Data Index: 28160 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.4767. Min Act: -0.1700
Data Index: 160472 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.4455. Min Act: -0.1700
Data Index: 5959823 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.4767. Min Act: -0.1700
Data Index: 273485 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.4455. Min Act: -0.1700
Data Index: 4712671 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.4142. Min Act: -0.1700
Data Index: 8556375 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.4142. Min Act: -0.1700
Data Index: 6876653 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.3830. Min Act: -0.1700
Data Index: 3555308 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.3830. Min Act: -0.1700
Data Index: 2269857 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.3830. Min Act: -0.1700
Data Index: 4764404 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.3517. Min Act: -0.1700
Data Index: 1573714 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.3517. Min Act: -0.1700
Data Index: 7493906 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.3205. Min Act: -0.1700
Data Index: 3907137 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.2892. Min Act: -0.1700
Data Index: 6517377 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.2892. Min Act: -0.1700
Data Index: 4098155 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.2892. Min Act: -0.1700
Data Index: 7398379 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.2892. Min Act: -0.1700
Data Index: 2702437 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.2892. Min Act: -0.1700
Data Index: 2463675 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.2580. Min Act: -0.1700
Data Index: 357448 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6017. Min Range: -6.6017
Max Act: 6.2580. Min Act: -0.1700
Data Index: 2926662 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19