Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5037 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.9794. Min Act: -0.1700
Data Index: 5694699 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.8543. Min Act: -0.1700
Data Index: 905742 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.8856. Min Act: -0.1700
Data Index: 7102334 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.8543. Min Act: -0.1700
Data Index: 875273 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.8543. Min Act: -0.1700
Data Index: 2241344 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.8543. Min Act: -0.1700
Data Index: 3089854 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.8543. Min Act: -0.1700
Data Index: 3471688 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.8230. Min Act: -0.1700
Data Index: 5637987 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.7761. Min Act: -0.1700
Data Index: 4059891 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.7605. Min Act: -0.1700
Data Index: 1976811 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.7605. Min Act: -0.1700
Data Index: 2525893 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.7761. Min Act: -0.1700
Data Index: 5096605 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.7448. Min Act: -0.1700
Data Index: 7598700 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.6979. Min Act: -0.1700
Data Index: 744896 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.7136. Min Act: -0.1700
Data Index: 3103003 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.7292. Min Act: -0.1700
Data Index: 6303007 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.7136. Min Act: -0.1700
Data Index: 4359233 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.6979. Min Act: -0.1700
Data Index: 2440218 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.6979. Min Act: -0.1700
Data Index: 7088389 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9794. Min Range: -3.9794
Max Act: 3.6979. Min Act: -0.1700
Data Index: 5517383 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19