Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1513. Min Range: -5.1513
Max Act: 5.1201. Min Act: -0.1700
Data Index: 3789927 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1513. Min Range: -5.1513
Max Act: 5.1513. Min Act: -0.1700
Data Index: 8518898 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1513. Min Range: -5.1513
Max Act: 5.1513. Min Act: -0.1700
Data Index: 16258 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1513. Min Range: -5.1513
Max Act: 5.0576. Min Act: -0.1700
Data Index: 5695464 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1513. Min Range: -5.1513
Max Act: 5.0576. Min Act: -0.1700
Data Index: 1591151 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1513. Min Range: -5.1513
Max Act: 5.0576. Min Act: -0.1700
Data Index: 1853256 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1513. Min Range: -5.1513
Max Act: 5.0263. Min Act: -0.1700
Data Index: 8514971 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1513. Min Range: -5.1513
Max Act: 5.0263. Min Act: -0.1700
Data Index: 3776385 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9951. Min Act: -0.1700
Data Index: 7557124 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9951. Min Act: -0.1700
Data Index: 5231891 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9951. Min Act: -0.1700
Data Index: 6290781 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9638. Min Act: -0.1700
Data Index: 7783053 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9638. Min Act: -0.1699
Data Index: 910827 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9638. Min Act: -0.1700
Data Index: 4676710 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9638. Min Act: -0.1700
Data Index: 1591161 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9638. Min Act: -0.1700
Data Index: 1591153 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9638. Min Act: -0.1700
Data Index: 3776383 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9638. Min Act: -0.1700
Data Index: 8347111 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9638. Min Act: -0.1700
Data Index: 914764 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1513. Min Range: -5.1513
Max Act: 4.9638. Min Act: -0.1700
Data Index: 151470 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19