Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5645. Min Range: -7.5645
Max Act: 7.5645. Min Act: -0.1700
Data Index: 6470915 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5645. Min Range: -7.5645
Max Act: 7.0645. Min Act: -0.1700
Data Index: 3530860 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.9707. Min Act: -0.1700
Data Index: 2171191 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.8457. Min Act: -0.1700
Data Index: 5395652 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.7207. Min Act: -0.1700
Data Index: 2220323 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.6895. Min Act: -0.1700
Data Index: 7872803 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.6270. Min Act: -0.1700
Data Index: 6575268 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.5645. Min Act: -0.1700
Data Index: 8649075 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.5645. Min Act: -0.1700
Data Index: 4438975 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.5957. Min Act: -0.1700
Data Index: 7870625 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.5332. Min Act: -0.1700
Data Index: 6191032 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.5020. Min Act: -0.1700
Data Index: 2875690 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.5020. Min Act: -0.1700
Data Index: 2597846 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.4707. Min Act: -0.1700
Data Index: 8779152 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.4707. Min Act: -0.1700
Data Index: 847649 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.4395. Min Act: -0.1700
Data Index: 7384119 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.4395. Min Act: -0.1700
Data Index: 1525700 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.4395. Min Act: -0.1700
Data Index: 6166809 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.4082. Min Act: -0.1700
Data Index: 3546509 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5645. Min Range: -7.5645
Max Act: 6.4082. Min Act: -0.1700
Data Index: 6011195 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19