Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2483 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4067. Min Range: -7.4067
Max Act: 7.4067. Min Act: -0.1700
Data Index: 2430946 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4067. Min Range: -7.4067
Max Act: 7.2505. Min Act: -0.1700
Data Index: 4443622 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4067. Min Range: -7.4067
Max Act: 7.1255. Min Act: -0.1700
Data Index: 1252419 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.9380. Min Act: -0.1700
Data Index: 2421682 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.8442. Min Act: -0.1700
Data Index: 7835222 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.8442. Min Act: -0.1700
Data Index: 5790537 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.7505. Min Act: -0.1700
Data Index: 1965478 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.7505. Min Act: -0.1700
Data Index: 4668182 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.7505. Min Act: -0.1700
Data Index: 508872 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.7505. Min Act: -0.1700
Data Index: 3964765 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.7192. Min Act: -0.1700
Data Index: 2942888 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.6880. Min Act: -0.1700
Data Index: 6128911 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.6880. Min Act: -0.1700
Data Index: 3286187 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.6567. Min Act: -0.1700
Data Index: 8658114 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.6255. Min Act: -0.1700
Data Index: 5591997 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.6255. Min Act: -0.1700
Data Index: 8729579 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.6255. Min Act: -0.1700
Data Index: 797767 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.6255. Min Act: -0.1700
Data Index: 1776013 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.5630. Min Act: -0.1700
Data Index: 4183816 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4067. Min Range: -7.4067
Max Act: 6.6255. Min Act: -0.1700
Data Index: 522789 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19