Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3838 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2074. Min Range: -5.2074
Max Act: 5.2074. Min Act: -0.1700
Data Index: 6391976 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2074. Min Range: -5.2074
Max Act: 5.1136. Min Act: -0.1700
Data Index: 456686 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2074. Min Range: -5.2074
Max Act: 5.0824. Min Act: -0.1700
Data Index: 1964897 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2074. Min Range: -5.2074
Max Act: 5.0511. Min Act: -0.1700
Data Index: 20460 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2074. Min Range: -5.2074
Max Act: 5.0511. Min Act: -0.1700
Data Index: 3120462 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2074. Min Range: -5.2074
Max Act: 5.0824. Min Act: -0.1700
Data Index: 2747542 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9886. Min Act: -0.1700
Data Index: 4022712 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2074. Min Range: -5.2074
Max Act: 5.0199. Min Act: -0.1700
Data Index: 359031 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9886. Min Act: -0.1700
Data Index: 2236764 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2074. Min Range: -5.2074
Max Act: 5.0199. Min Act: -0.1700
Data Index: 586534 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9886. Min Act: -0.1700
Data Index: 6794145 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9886. Min Act: -0.1700
Data Index: 6670875 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9886. Min Act: -0.1700
Data Index: 8138909 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9886. Min Act: -0.1700
Data Index: 2145080 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9886. Min Act: -0.1700
Data Index: 3756755 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9574. Min Act: -0.1700
Data Index: 7645054 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9261. Min Act: -0.1700
Data Index: 4287705 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9261. Min Act: -0.1700
Data Index: 3233199 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9261. Min Act: -0.1700
Data Index: 8095386 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2074. Min Range: -5.2074
Max Act: 4.9574. Min Act: -0.1700
Data Index: 2790044 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19