Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4002 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.5757. Min Act: -0.1700
Data Index: 940238 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.5132. Min Act: -0.1700
Data Index: 2519642 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.3257. Min Act: -0.1700
Data Index: 3295087 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.2632. Min Act: -0.1700
Data Index: 6254541 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.2007. Min Act: -0.1700
Data Index: 7005410 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.1695. Min Act: -0.1700
Data Index: 7329254 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.1695. Min Act: -0.1700
Data Index: 3334861 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.0757. Min Act: -0.1700
Data Index: 2036508 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.0445. Min Act: -0.1700
Data Index: 1148581 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.0132. Min Act: -0.1700
Data Index: 63844 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.0132. Min Act: -0.1700
Data Index: 8758182 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5757. Min Range: -8.5757
Max Act: 8.0132. Min Act: -0.1700
Data Index: 1092031 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5757. Min Range: -8.5757
Max Act: 7.9195. Min Act: -0.1700
Data Index: 3474191 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5757. Min Range: -8.5757
Max Act: 7.9507. Min Act: -0.1700
Data Index: 485784 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5757. Min Range: -8.5757
Max Act: 7.9507. Min Act: -0.1700
Data Index: 7941929 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5757. Min Range: -8.5757
Max Act: 7.8882. Min Act: -0.1700
Data Index: 7355003 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5757. Min Range: -8.5757
Max Act: 7.8570. Min Act: -0.1700
Data Index: 6231109 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5757. Min Range: -8.5757
Max Act: 7.8257. Min Act: -0.1700
Data Index: 4554107 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5757. Min Range: -8.5757
Max Act: 7.8257. Min Act: -0.1700
Data Index: 4910692 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5757. Min Range: -8.5757
Max Act: 7.8257. Min Act: -0.1700
Data Index: 8737458 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19