Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3152 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.1721. Min Act: -0.1700
Data Index: 178625 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.1721. Min Act: -0.1700
Data Index: 261608 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.1554. Min Act: -0.1700
Data Index: 1782214 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.1054. Min Act: -0.1700
Data Index: 2994181 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.0718. Min Act: -0.1700
Data Index: 6189012 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.0550. Min Act: -0.1700
Data Index: 3405076 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.0213. Min Act: -0.1700
Data Index: 5204825 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.0045. Min Act: -0.1700
Data Index: 7160310 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.0045. Min Act: -0.1700
Data Index: 7774080 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1721. Min Range: -2.1721
Max Act: 2.0045. Min Act: -0.1700
Data Index: 3648511 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9876. Min Act: -0.1700
Data Index: 2834374 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9706. Min Act: -0.1700
Data Index: 8612862 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9706. Min Act: -0.1700
Data Index: 3082215 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9876. Min Act: -0.1700
Data Index: 5967834 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9537. Min Act: -0.1700
Data Index: 1241571 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9537. Min Act: -0.1700
Data Index: 8825275 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9706. Min Act: -0.1700
Data Index: 6156451 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9367. Min Act: -0.1700
Data Index: 6373139 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9367. Min Act: -0.1700
Data Index: 3850693 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1721. Min Range: -2.1721
Max Act: 1.9026. Min Act: -0.1700
Data Index: 1179772 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19