Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 830 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.5738. Min Act: -0.1700
Data Index: 7488762 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.5353. Min Act: -0.1694
Data Index: 816600 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.5276. Min Act: -0.1700
Data Index: 8661225 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.5125. Min Act: -0.1700
Data Index: 480672 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.5049. Min Act: -0.1700
Data Index: 4478726 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4899. Min Act: -0.1700
Data Index: 7618182 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4825. Min Act: -0.1700
Data Index: 6048248 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4899. Min Act: -0.1700
Data Index: 2783487 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4825. Min Act: -0.1700
Data Index: 3175747 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4825. Min Act: -0.1700
Data Index: 6105061 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4825. Min Act: -0.1694
Data Index: 2318465 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4825. Min Act: -0.1700
Data Index: 3409593 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4750. Min Act: -0.1699
Data Index: 6434806 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4750. Min Act: -0.1691
Data Index: 2692914 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4750. Min Act: -0.1700
Data Index: 249245 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4677. Min Act: -0.1694
Data Index: 7088317 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4750. Min Act: -0.1700
Data Index: 869034 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4603. Min Act: -0.1700
Data Index: 6390987 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4677. Min Act: -0.1687
Data Index: 4707556 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5738. Min Range: -0.5738
Max Act: 0.4750. Min Act: -0.1700
Data Index: 442906 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19