Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 219 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1567. Min Range: -8.1567
Max Act: 8.1567. Min Act: -0.1700
Data Index: 8425442 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1567. Min Range: -8.1567
Max Act: 8.0942. Min Act: -0.1700
Data Index: 3293258 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.9692. Min Act: -0.1700
Data Index: 4432022 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.8129. Min Act: -0.1700
Data Index: 1251107 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.6567. Min Act: -0.1700
Data Index: 7270145 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.6567. Min Act: -0.1700
Data Index: 2449641 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.5317. Min Act: -0.1700
Data Index: 144877 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.5629. Min Act: -0.1700
Data Index: 4802375 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.5317. Min Act: -0.1700
Data Index: 4131180 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.4692. Min Act: -0.1700
Data Index: 5101726 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.4692. Min Act: -0.1700
Data Index: 658001 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.4379. Min Act: -0.1700
Data Index: 3544568 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.4379. Min Act: -0.1700
Data Index: 3853585 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.4067. Min Act: -0.1700
Data Index: 7171433 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.4067. Min Act: -0.1700
Data Index: 2888987 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.3754. Min Act: -0.1700
Data Index: 3028651 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.4067. Min Act: -0.1700
Data Index: 246395 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.3442. Min Act: -0.1700
Data Index: 4029141 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.3442. Min Act: -0.1700
Data Index: 5587357 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1567. Min Range: -8.1567
Max Act: 7.3442. Min Act: -0.1700
Data Index: 7700790 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19