Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4131 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.9455. Min Act: -0.1700
Data Index: 1335449 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.7267. Min Act: -0.1700
Data Index: 7127243 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.7267. Min Act: -0.1700
Data Index: 4823909 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6642. Min Act: -0.1700
Data Index: 4642893 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6642. Min Act: -0.1700
Data Index: 2305924 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6642. Min Act: -0.1700
Data Index: 272564 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6642. Min Act: -0.1700
Data Index: 5808329 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6955. Min Act: -0.1700
Data Index: 3443912 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6330. Min Act: -0.1700
Data Index: 3864770 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6642. Min Act: -0.1700
Data Index: 3872225 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6017. Min Act: -0.1700
Data Index: 7015763 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6330. Min Act: -0.1700
Data Index: 6456408 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5705. Min Act: -0.1700
Data Index: 81001 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6017. Min Act: -0.1700
Data Index: 8515470 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6017. Min Act: -0.1700
Data Index: 8087647 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5705. Min Act: -0.1700
Data Index: 2146477 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5392. Min Act: -0.1700
Data Index: 8750496 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5392. Min Act: -0.1700
Data Index: 2153015 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5392. Min Act: -0.1700
Data Index: 2634679 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5080. Min Act: -0.1700
Data Index: 3281617 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19