Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.9846. Min Act: -0.1700
Data Index: 7445741 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.4846. Min Act: -0.1700
Data Index: 4845981 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.4846. Min Act: -0.1700
Data Index: 2776370 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.4221. Min Act: -0.1700
Data Index: 8791497 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.4221. Min Act: -0.1700
Data Index: 1102703 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.4846. Min Act: -0.1700
Data Index: 5584215 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.3596. Min Act: -0.1700
Data Index: 981791 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.3596. Min Act: -0.1700
Data Index: 529473 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.3596. Min Act: -0.1700
Data Index: 1884658 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2971. Min Act: -0.1700
Data Index: 622110 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2971. Min Act: -0.1700
Data Index: 5955406 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2971. Min Act: -0.1700
Data Index: 2404484 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2346. Min Act: -0.1700
Data Index: 126427 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2346. Min Act: -0.1700
Data Index: 6820701 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2346. Min Act: -0.1700
Data Index: 5379849 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2346. Min Act: -0.1700
Data Index: 4720026 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2346. Min Act: -0.1700
Data Index: 6837906 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2346. Min Act: -0.1700
Data Index: 8669850 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2346. Min Act: -0.1700
Data Index: 97825 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9846. Min Range: -9.9846
Max Act: 9.2346. Min Act: -0.1700
Data Index: 6158234 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19