Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2227 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.9891. Min Act: -0.1687
Data Index: 2792191 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.7391. Min Act: -0.1700
Data Index: 6939443 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0516. Min Range: -8.0516
Max Act: 8.0516. Min Act: -0.1700
Data Index: 6178594 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.3641. Min Act: -0.1700
Data Index: 955098 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.7391. Min Act: -0.1700
Data Index: 4991909 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.5516. Min Act: -0.1700
Data Index: 7287365 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.4891. Min Act: -0.1700
Data Index: 4991908 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.3641. Min Act: -0.1699
Data Index: 4311310 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.5516. Min Act: -0.1700
Data Index: 952392 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.5516. Min Act: -0.1700
Data Index: 5667611 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.1766. Min Act: -0.1700
Data Index: 6714488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0516. Min Range: -8.0516
Max Act: 6.6453. Min Act: -0.1700
Data Index: 8636001 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.1766. Min Act: -0.1696
Data Index: 4615018 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.4891. Min Act: -0.1700
Data Index: 7125048 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0516. Min Range: -8.0516
Max Act: 6.6766. Min Act: -0.1700
Data Index: 6939444 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.0828. Min Act: -0.1700
Data Index: 291220 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.0828. Min Act: -0.1700
Data Index: 5320801 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.1766. Min Act: -0.1699
Data Index: 6420116 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.0516. Min Act: -0.1700
Data Index: 6420126 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0516. Min Range: -8.0516
Max Act: 6.7703. Min Act: -0.1699
Data Index: 4368140 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19