Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.7973. Min Act: -0.1700
Data Index: 2511912 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.7973. Min Act: -0.1700
Data Index: 2728464 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.7661. Min Act: -0.1700
Data Index: 1677882 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.6723. Min Act: -0.1700
Data Index: 982589 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.5473. Min Act: -0.1700
Data Index: 6781629 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.4536. Min Act: -0.1700
Data Index: 2688237 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.3911. Min Act: -0.1700
Data Index: 5586482 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.3286. Min Act: -0.1700
Data Index: 4377912 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2973. Min Act: -0.1700
Data Index: 4794829 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2661. Min Act: -0.1700
Data Index: 7023045 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2661. Min Act: -0.1700
Data Index: 5818235 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2661. Min Act: -0.1700
Data Index: 6310214 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2348. Min Act: -0.1700
Data Index: 5243972 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2348. Min Act: -0.1700
Data Index: 8660319 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2348. Min Act: -0.1700
Data Index: 1533625 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2036. Min Act: -0.1700
Data Index: 2437743 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2036. Min Act: -0.1700
Data Index: 5840206 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.2036. Min Act: -0.1700
Data Index: 2665756 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.1411. Min Act: -0.1700
Data Index: 8020212 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7973. Min Range: -6.7973
Max Act: 6.1411. Min Act: -0.1700
Data Index: 7282439 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19