Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3931 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.8730. Min Act: -0.1700
Data Index: 4284814 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.8094. Min Act: -0.1700
Data Index: 4505142 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7775. Min Act: -0.1700
Data Index: 7670742 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 2368018 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 6444063 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7616. Min Act: -0.1700
Data Index: 1185920 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 1250074 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 2050730 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 1743770 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7297. Min Act: -0.1700
Data Index: 1696456 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 1633919 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7616. Min Act: -0.1700
Data Index: 2906156 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 7888437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 5827746 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 2651942 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7297. Min Act: -0.1700
Data Index: 7617180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 7159997 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 4847969 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7456. Min Act: -0.1700
Data Index: 1398688 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8730. Min Range: -2.8730
Max Act: 2.7137. Min Act: -0.1700
Data Index: 6150701 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19