Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4438 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.8799. Min Act: -0.1700
Data Index: 3297623 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.8174. Min Act: -0.1700
Data Index: 7774486 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.7549. Min Act: -0.1700
Data Index: 967144 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.7237. Min Act: -0.1700
Data Index: 7814114 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.7237. Min Act: -0.1700
Data Index: 1357201 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.6924. Min Act: -0.1700
Data Index: 2305879 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.6612. Min Act: -0.1700
Data Index: 3965991 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.6299. Min Act: -0.1700
Data Index: 4592877 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.6612. Min Act: -0.1700
Data Index: 6348280 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.5987. Min Act: -0.1700
Data Index: 8696226 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.5674. Min Act: -0.1700
Data Index: 7530873 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.5049. Min Act: -0.1700
Data Index: 5571979 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.4424. Min Act: -0.1700
Data Index: 7344078 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.4424. Min Act: -0.1700
Data Index: 6371547 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.4424. Min Act: -0.1700
Data Index: 6546613 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.4112. Min Act: -0.1700
Data Index: 266803 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.4112. Min Act: -0.1700
Data Index: 7839316 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.4112. Min Act: -0.1700
Data Index: 4865809 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.4112. Min Act: -0.1700
Data Index: 3865045 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8799. Min Range: -7.8799
Max Act: 7.4112. Min Act: -0.1700
Data Index: 564515 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19