Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.3738. Min Act: -0.1700
Data Index: 1135236 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.3113. Min Act: -0.1700
Data Index: 1618406 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.3113. Min Act: -0.1700
Data Index: 1175542 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2800. Min Act: -0.1700
Data Index: 5420466 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2488. Min Act: -0.1700
Data Index: 2156108 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2800. Min Act: -0.1700
Data Index: 1681171 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2488. Min Act: -0.1700
Data Index: 2149890 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2488. Min Act: -0.1700
Data Index: 1776158 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2488. Min Act: -0.1700
Data Index: 6815735 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2488. Min Act: -0.1700
Data Index: 2272023 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2175. Min Act: -0.1700
Data Index: 2883807 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2175. Min Act: -0.1700
Data Index: 7621862 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2488. Min Act: -0.1700
Data Index: 2641870 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2175. Min Act: -0.1700
Data Index: 925586 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2175. Min Act: -0.1700
Data Index: 1736962 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2175. Min Act: -0.1700
Data Index: 8743934 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.1863. Min Act: -0.1700
Data Index: 2240970 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2175. Min Act: -0.1700
Data Index: 628159 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.2175. Min Act: -0.1700
Data Index: 6224615 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3738. Min Range: -4.3738
Max Act: 4.1863. Min Act: -0.1700
Data Index: 5582220 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19