Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.9318. Min Act: -0.1698
Data Index: 5648975 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.8068. Min Act: -0.1700
Data Index: 4288892 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.5568. Min Act: -0.1700
Data Index: 1616893 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.5255. Min Act: -0.1700
Data Index: 5721474 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.5255. Min Act: -0.1700
Data Index: 3281682 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.4318. Min Act: -0.1700
Data Index: 6397699 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.4318. Min Act: -0.1700
Data Index: 7065146 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.4318. Min Act: -0.1694
Data Index: 7844933 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.4318. Min Act: -0.1700
Data Index: 7658119 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.4005. Min Act: -0.1686
Data Index: 5986463 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.3693. Min Act: -0.1700
Data Index: 3166242 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.3380. Min Act: -0.1699
Data Index: 4677200 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.3380. Min Act: -0.1700
Data Index: 6337137 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.3380. Min Act: -0.1699
Data Index: 574391 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.3380. Min Act: -0.1683
Data Index: 6774853 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.3693. Min Act: -0.1698
Data Index: 795345 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.3380. Min Act: -0.1692
Data Index: 8349360 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.3068. Min Act: -0.1700
Data Index: 3201494 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.3380. Min Act: -0.1694
Data Index: 5625787 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9318. Min Range: -4.9318
Max Act: 4.2755. Min Act: -0.1699
Data Index: 2646495 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19