Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0455. Min Range: -9.0455
Max Act: 9.0455. Min Act: -0.1700
Data Index: 3065897 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.8580. Min Act: -0.1700
Data Index: 510294 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.8580. Min Act: -0.1700
Data Index: 868264 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.7330. Min Act: -0.1700
Data Index: 760723 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.7330. Min Act: -0.1700
Data Index: 1556178 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.7330. Min Act: -0.1700
Data Index: 5297108 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.6705. Min Act: -0.1700
Data Index: 2771423 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.6705. Min Act: -0.1700
Data Index: 6473074 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.6705. Min Act: -0.1700
Data Index: 6050390 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.6080. Min Act: -0.1700
Data Index: 295848 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.6080. Min Act: -0.1700
Data Index: 4861423 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.6080. Min Act: -0.1700
Data Index: 6767423 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.6080. Min Act: -0.1700
Data Index: 8695440 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.4830. Min Act: -0.1700
Data Index: 4432551 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.4830. Min Act: -0.1700
Data Index: 106137 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.4830. Min Act: -0.1700
Data Index: 783885 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.4830. Min Act: -0.1700
Data Index: 5431445 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.4830. Min Act: -0.1700
Data Index: 3758840 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.4830. Min Act: -0.1700
Data Index: 328936 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0455. Min Range: -9.0455
Max Act: 8.4830. Min Act: -0.1700
Data Index: 1195837 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19