Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2455 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5639. Min Range: -8.5639
Max Act: 8.5639. Min Act: -0.1700
Data Index: 3663388 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5639. Min Range: -8.5639
Max Act: 8.1889. Min Act: -0.1700
Data Index: 4323901 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5639. Min Range: -8.5639
Max Act: 8.1264. Min Act: -0.1700
Data Index: 3731931 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5639. Min Range: -8.5639
Max Act: 8.0639. Min Act: -0.1700
Data Index: 2112829 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5639. Min Range: -8.5639
Max Act: 8.0639. Min Act: -0.1700
Data Index: 2369167 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.9702. Min Act: -0.1700
Data Index: 8502618 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5639. Min Range: -8.5639
Max Act: 8.0014. Min Act: -0.1700
Data Index: 6150473 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.9389. Min Act: -0.1700
Data Index: 8081099 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.9702. Min Act: -0.1700
Data Index: 4443879 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.9702. Min Act: -0.1700
Data Index: 4733886 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.9389. Min Act: -0.1700
Data Index: 3286393 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.9077. Min Act: -0.1700
Data Index: 864581 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.9077. Min Act: -0.1700
Data Index: 6150463 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.8452. Min Act: -0.1700
Data Index: 5982145 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.8452. Min Act: -0.1700
Data Index: 2673343 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.9077. Min Act: -0.1700
Data Index: 6241660 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.8452. Min Act: -0.1700
Data Index: 879567 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.8452. Min Act: -0.1700
Data Index: 1850610 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.8139. Min Act: -0.1700
Data Index: 5026318 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5639. Min Range: -8.5639
Max Act: 7.8452. Min Act: -0.1700
Data Index: 2936764 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19