Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.6879. Min Act: -0.1700
Data Index: 584294 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.5317. Min Act: -0.1700
Data Index: 5990055 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.5317. Min Act: -0.1700
Data Index: 7602447 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.5629. Min Act: -0.1700
Data Index: 7532506 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.5317. Min Act: -0.1700
Data Index: 7349883 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.5004. Min Act: -0.1700
Data Index: 7409971 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.4692. Min Act: -0.1700
Data Index: 142908 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.4692. Min Act: -0.1700
Data Index: 5417233 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.4067. Min Act: -0.1700
Data Index: 5417235 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.4067. Min Act: -0.1700
Data Index: 7709426 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.4067. Min Act: -0.1700
Data Index: 5990049 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.3129. Min Act: -0.1700
Data Index: 2122330 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.3129. Min Act: -0.1700
Data Index: 8342824 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.3129. Min Act: -0.1700
Data Index: 5417234 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.3129. Min Act: -0.1700
Data Index: 5626436 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.3129. Min Act: -0.1700
Data Index: 276167 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.2817. Min Act: -0.1700
Data Index: 3084700 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.2817. Min Act: -0.1700
Data Index: 5598365 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.2817. Min Act: -0.1700
Data Index: 142917 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6879. Min Range: -5.6879
Max Act: 5.2817. Min Act: -0.1700
Data Index: 7602448 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19