Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3977 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.9664. Min Act: -0.1700
Data Index: 5228084 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.8414. Min Act: -0.1700
Data Index: 3043908 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.9039. Min Act: -0.1700
Data Index: 1117252 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.7789. Min Act: -0.1700
Data Index: 4780118 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.7789. Min Act: -0.1700
Data Index: 194228 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.7164. Min Act: -0.1700
Data Index: 2232479 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.7164. Min Act: -0.1700
Data Index: 5630032 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.6539. Min Act: -0.1700
Data Index: 465468 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.5914. Min Act: -0.1700
Data Index: 1732933 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.5914. Min Act: -0.1700
Data Index: 8231340 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.5289. Min Act: -0.1700
Data Index: 786886 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.5289. Min Act: -0.1700
Data Index: 5486278 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.5289. Min Act: -0.1700
Data Index: 4000245 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.5289. Min Act: -0.1700
Data Index: 4787224 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.4039. Min Act: -0.1700
Data Index: 995570 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.4664. Min Act: -0.1700
Data Index: 1688533 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.4664. Min Act: -0.1700
Data Index: 1631896 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.4664. Min Act: -0.1700
Data Index: 182581 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.4664. Min Act: -0.1700
Data Index: 670832 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9664. Min Range: -8.9664
Max Act: 8.4039. Min Act: -0.1700
Data Index: 6626783 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19