Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5414 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.7180. Min Act: -0.1700
Data Index: 5185648 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.6867. Min Act: -0.1700
Data Index: 8164991 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.5617. Min Act: -0.1700
Data Index: 5060892 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.5305. Min Act: -0.1700
Data Index: 349492 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.5305. Min Act: -0.1700
Data Index: 1195709 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.4992. Min Act: -0.1700
Data Index: 4385571 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.4367. Min Act: -0.1700
Data Index: 6106361 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.4367. Min Act: -0.1700
Data Index: 2971676 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.4055. Min Act: -0.1700
Data Index: 4848324 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.4055. Min Act: -0.1700
Data Index: 2293866 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.3742. Min Act: -0.1700
Data Index: 2204655 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.4055. Min Act: -0.1700
Data Index: 4483450 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.3430. Min Act: -0.1700
Data Index: 1457323 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.3742. Min Act: -0.1700
Data Index: 527447 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.3430. Min Act: -0.1700
Data Index: 2431538 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.3430. Min Act: -0.1700
Data Index: 1677336 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.3117. Min Act: -0.1700
Data Index: 7953995 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.3117. Min Act: -0.1700
Data Index: 6067287 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.3117. Min Act: -0.1700
Data Index: 5858440 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7180. Min Range: -5.7180
Max Act: 5.3117. Min Act: -0.1700
Data Index: 4249259 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19