Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.2540. Min Act: -0.1700
Data Index: 3196716 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.2540. Min Act: -0.1700
Data Index: 4022249 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.1603. Min Act: -0.1700
Data Index: 612737 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0978. Min Act: -0.1700
Data Index: 1585283 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0978. Min Act: -0.1700
Data Index: 3392117 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0978. Min Act: -0.1700
Data Index: 8272983 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0353. Min Act: -0.1700
Data Index: 8590030 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0665. Min Act: -0.1700
Data Index: 7218434 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0978. Min Act: -0.1700
Data Index: 4988499 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0353. Min Act: -0.1700
Data Index: 4967483 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0665. Min Act: -0.1700
Data Index: 2463334 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0353. Min Act: -0.1700
Data Index: 7925198 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0353. Min Act: -0.1700
Data Index: 5094786 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0353. Min Act: -0.1700
Data Index: 5141016 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0353. Min Act: -0.1700
Data Index: 8242081 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0040. Min Act: -0.1700
Data Index: 3995655 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0040. Min Act: -0.1700
Data Index: 2129069 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2540. Min Range: -5.2540
Max Act: 4.9728. Min Act: -0.1700
Data Index: 7544107 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2540. Min Range: -5.2540
Max Act: 5.0040. Min Act: -0.1700
Data Index: 6323721 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2540. Min Range: -5.2540
Max Act: 4.9728. Min Act: -0.1700
Data Index: 5032888 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19