Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3997 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.5500. Min Act: -0.1700
Data Index: 3716451 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.4403. Min Act: -0.1700
Data Index: 7684514 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.3776. Min Act: -0.1700
Data Index: 5014236 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.3933. Min Act: -0.1700
Data Index: 7429158 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.3306. Min Act: -0.1700
Data Index: 5200172 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.3149. Min Act: -0.1700
Data Index: 2824548 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2521. Min Act: -0.1700
Data Index: 8120864 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2363. Min Act: -0.1700
Data Index: 8610313 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2521. Min Act: -0.1700
Data Index: 949390 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2206. Min Act: -0.1700
Data Index: 4334469 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2363. Min Act: -0.1700
Data Index: 7927888 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2049. Min Act: -0.1700
Data Index: 8046552 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2206. Min Act: -0.1700
Data Index: 6780781 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2049. Min Act: -0.1700
Data Index: 5834183 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2049. Min Act: -0.1700
Data Index: 4393473 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2049. Min Act: -0.1700
Data Index: 2520140 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.2049. Min Act: -0.1700
Data Index: 6305627 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.1892. Min Act: -0.1700
Data Index: 3838722 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.1892. Min Act: -0.1700
Data Index: 7722256 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5500. Min Range: -3.5500
Max Act: 3.1892. Min Act: -0.1700
Data Index: 6775557 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19