Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3287. Min Range: -7.3287
Max Act: 7.3287. Min Act: -0.1700
Data Index: 5156358 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3287. Min Range: -7.3287
Max Act: 7.2349. Min Act: -0.1700
Data Index: 6983871 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3287. Min Range: -7.3287
Max Act: 7.2662. Min Act: -0.1700
Data Index: 1150590 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3287. Min Range: -7.3287
Max Act: 7.0787. Min Act: -0.1700
Data Index: 4539292 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3287. Min Range: -7.3287
Max Act: 7.0474. Min Act: -0.1700
Data Index: 2587596 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.9849. Min Act: -0.1700
Data Index: 4460338 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.9537. Min Act: -0.1700
Data Index: 2054541 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.9537. Min Act: -0.1700
Data Index: 5440130 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8912. Min Act: -0.1700
Data Index: 8157704 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.9224. Min Act: -0.1700
Data Index: 4618922 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8912. Min Act: -0.1700
Data Index: 1944889 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8912. Min Act: -0.1700
Data Index: 3058846 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8912. Min Act: -0.1700
Data Index: 4539293 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8599. Min Act: -0.1700
Data Index: 5584503 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8287. Min Act: -0.1700
Data Index: 1749168 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8287. Min Act: -0.1700
Data Index: 3316892 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8287. Min Act: -0.1700
Data Index: 105911 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8287. Min Act: -0.1700
Data Index: 3614652 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.8287. Min Act: -0.1700
Data Index: 7744221 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3287. Min Range: -7.3287
Max Act: 6.7974. Min Act: -0.1700
Data Index: 4102270 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19