Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5020 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.7467. Min Act: -0.1700
Data Index: 167716 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.5592. Min Act: -0.1700
Data Index: 6790165 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.5592. Min Act: -0.1700
Data Index: 2996530 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.4342. Min Act: -0.1700
Data Index: 987111 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.4029. Min Act: -0.1700
Data Index: 4309700 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.4029. Min Act: -0.1700
Data Index: 7911670 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.4029. Min Act: -0.1700
Data Index: 6610530 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.3404. Min Act: -0.1700
Data Index: 6327226 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.3092. Min Act: -0.1700
Data Index: 3547232 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.2779. Min Act: -0.1700
Data Index: 2312824 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.2467. Min Act: -0.1700
Data Index: 2495699 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.2154. Min Act: -0.1700
Data Index: 315741 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.2467. Min Act: -0.1700
Data Index: 1032978 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.1842. Min Act: -0.1700
Data Index: 5794325 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.1842. Min Act: -0.1700
Data Index: 4208761 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.1842. Min Act: -0.1700
Data Index: 3468320 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.1842. Min Act: -0.1700
Data Index: 5127131 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.1529. Min Act: -0.1700
Data Index: 909676 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.1217. Min Act: -0.1700
Data Index: 6268610 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7467. Min Range: -7.7467
Max Act: 7.1217. Min Act: -0.1700
Data Index: 2400103 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19