Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4359 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3313. Min Range: -7.3313
Max Act: 7.3313. Min Act: -0.1700
Data Index: 2059996 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3313. Min Range: -7.3313
Max Act: 7.0188. Min Act: -0.1700
Data Index: 3724963 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.8313. Min Act: -0.1700
Data Index: 7483729 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.7376. Min Act: -0.1700
Data Index: 4732197 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.7376. Min Act: -0.1700
Data Index: 4641783 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.7063. Min Act: -0.1700
Data Index: 3018134 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.6751. Min Act: -0.1700
Data Index: 1443149 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.6751. Min Act: -0.1700
Data Index: 2956636 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.5813. Min Act: -0.1700
Data Index: 2493236 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.5501. Min Act: -0.1700
Data Index: 8221809 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.5188. Min Act: -0.1700
Data Index: 2430606 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.5188. Min Act: -0.1700
Data Index: 3843284 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.4876. Min Act: -0.1700
Data Index: 4760259 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.4563. Min Act: -0.1700
Data Index: 6802474 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.4251. Min Act: -0.1700
Data Index: 73963 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.4563. Min Act: -0.1700
Data Index: 4774855 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.4563. Min Act: -0.1700
Data Index: 6375055 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.4563. Min Act: -0.1700
Data Index: 1853902 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.4251. Min Act: -0.1700
Data Index: 7544287 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.3938. Min Act: -0.1700
Data Index: 153997 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19