Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5082. Min Range: -8.5082
Max Act: 8.5082. Min Act: -0.1700
Data Index: 5031892 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5082. Min Range: -8.5082
Max Act: 8.3832. Min Act: -0.1700
Data Index: 1798818 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.8207. Min Act: -0.1700
Data Index: 843854 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.7895. Min Act: -0.1700
Data Index: 7207661 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.6332. Min Act: -0.1700
Data Index: 6270961 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.6020. Min Act: -0.1700
Data Index: 7555779 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.5707. Min Act: -0.1700
Data Index: 3358085 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.5395. Min Act: -0.1700
Data Index: 26473 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.4770. Min Act: -0.1700
Data Index: 5093382 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.4770. Min Act: -0.1700
Data Index: 6280348 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.4457. Min Act: -0.1700
Data Index: 8201976 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.4145. Min Act: -0.1700
Data Index: 2833633 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.3832. Min Act: -0.1700
Data Index: 7795177 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.3207. Min Act: -0.1700
Data Index: 7879035 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.3520. Min Act: -0.1700
Data Index: 4157964 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.2895. Min Act: -0.1700
Data Index: 3249305 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.3207. Min Act: -0.1700
Data Index: 6774340 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.2582. Min Act: -0.1700
Data Index: 5051435 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.2582. Min Act: -0.1700
Data Index: 7654011 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5082. Min Range: -8.5082
Max Act: 7.2582. Min Act: -0.1700
Data Index: 3093216 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19