Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5912 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.4755. Min Act: -0.1700
Data Index: 6280138 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.5068. Min Act: -0.1700
Data Index: 2394056 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.4130. Min Act: -0.1700
Data Index: 2162095 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.4130. Min Act: -0.1700
Data Index: 2050714 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.3505. Min Act: -0.1700
Data Index: 8179024 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.3505. Min Act: -0.1697
Data Index: 8739435 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.3193. Min Act: -0.1700
Data Index: 7796941 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.3505. Min Act: -0.1700
Data Index: 2536699 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.3193. Min Act: -0.1700
Data Index: 8375466 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.3193. Min Act: -0.1700
Data Index: 6679155 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2880. Min Act: -0.1700
Data Index: 1251925 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2880. Min Act: -0.1695
Data Index: 7304803 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2880. Min Act: -0.1700
Data Index: 2359558 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2880. Min Act: -0.1700
Data Index: 1251926 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2880. Min Act: -0.1700
Data Index: 8614729 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2568. Min Act: -0.1700
Data Index: 2960401 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2568. Min Act: -0.1700
Data Index: 2050715 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2568. Min Act: -0.1700
Data Index: 8151750 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2568. Min Act: -0.1700
Data Index: 5534814 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5068. Min Range: -6.5068
Max Act: 6.2255. Min Act: -0.1700
Data Index: 7256192 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19