Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5832 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1714. Min Range: -7.1714
Max Act: 7.1714. Min Act: -0.1700
Data Index: 8070189 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1714. Min Range: -7.1714
Max Act: 7.0464. Min Act: -0.1700
Data Index: 4079516 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.7652. Min Act: -0.1700
Data Index: 7908366 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.7652. Min Act: -0.1700
Data Index: 3645698 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.7339. Min Act: -0.1700
Data Index: 7679478 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.7027. Min Act: -0.1700
Data Index: 6823634 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.7027. Min Act: -0.1700
Data Index: 6502824 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.6714. Min Act: -0.1700
Data Index: 7563021 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.6714. Min Act: -0.1700
Data Index: 415208 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.6714. Min Act: -0.1700
Data Index: 7493656 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.6089. Min Act: -0.1700
Data Index: 4373714 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.6089. Min Act: -0.1700
Data Index: 6587420 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.5777. Min Act: -0.1700
Data Index: 5282374 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.5152. Min Act: -0.1700
Data Index: 4459485 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.5464. Min Act: -0.1700
Data Index: 6058869 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.4839. Min Act: -0.1700
Data Index: 652080 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.4839. Min Act: -0.1700
Data Index: 4747165 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.4527. Min Act: -0.1700
Data Index: 4761766 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.4527. Min Act: -0.1700
Data Index: 7879395 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1714. Min Range: -7.1714
Max Act: 6.4527. Min Act: -0.1700
Data Index: 1111047 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19