Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4871 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.0868. Min Act: -0.1700
Data Index: 5774233 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.0868. Min Act: -0.1700
Data Index: 8791665 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.0868. Min Act: -0.1700
Data Index: 4353671 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.1493. Min Act: -0.1700
Data Index: 5296543 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.0243. Min Act: -0.1700
Data Index: 559251 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.0243. Min Act: -0.1700
Data Index: 1639629 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.0243. Min Act: -0.1700
Data Index: 7179665 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.0243. Min Act: -0.1700
Data Index: 1053743 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.0243. Min Act: -0.1700
Data Index: 2471904 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1493. Min Range: -10.1493
Max Act: 10.0243. Min Act: -0.1700
Data Index: 4193148 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.7743. Min Act: -0.1700
Data Index: 508212 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.7743. Min Act: -0.1700
Data Index: 7781034 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.7118. Min Act: -0.1700
Data Index: 2678119 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.5868. Min Act: -0.1700
Data Index: 7367850 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.5868. Min Act: -0.1700
Data Index: 2755082 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.5243. Min Act: -0.1700
Data Index: 5944097 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.5243. Min Act: -0.1700
Data Index: 1118724 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.5243. Min Act: -0.1700
Data Index: 3541768 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.4618. Min Act: -0.1700
Data Index: 7666254 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1493. Min Range: -10.1493
Max Act: 9.4618. Min Act: -0.1700
Data Index: 4302194 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19