Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5127 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1885. Min Range: -9.1885
Max Act: 9.1885. Min Act: -0.1700
Data Index: 4236849 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1885. Min Range: -9.1885
Max Act: 8.8760. Min Act: -0.1700
Data Index: 5157254 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1885. Min Range: -9.1885
Max Act: 8.4385. Min Act: -0.1700
Data Index: 706083 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1885. Min Range: -9.1885
Max Act: 8.3760. Min Act: -0.1700
Data Index: 513969 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1885. Min Range: -9.1885
Max Act: 8.3760. Min Act: -0.1700
Data Index: 706070 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1885. Min Range: -9.1885
Max Act: 8.2510. Min Act: -0.1700
Data Index: 140899 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1885. Min Range: -9.1885
Max Act: 8.1260. Min Act: -0.1700
Data Index: 3153655 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1885. Min Range: -9.1885
Max Act: 8.0635. Min Act: -0.1700
Data Index: 3991004 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1885. Min Range: -9.1885
Max Act: 8.0010. Min Act: -0.1700
Data Index: 400300 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1885. Min Range: -9.1885
Max Act: 8.0635. Min Act: -0.1700
Data Index: 3211552 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.9385. Min Act: -0.1700
Data Index: 2818043 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.9385. Min Act: -0.1700
Data Index: 2142321 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.9385. Min Act: -0.1700
Data Index: 225559 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.8760. Min Act: -0.1700
Data Index: 6968148 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.8447. Min Act: -0.1700
Data Index: 3346050 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.8447. Min Act: -0.1700
Data Index: 7558335 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.8447. Min Act: -0.1700
Data Index: 2916774 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.8135. Min Act: -0.1700
Data Index: 1294608 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.7822. Min Act: -0.1700
Data Index: 706088 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1885. Min Range: -9.1885
Max Act: 7.7510. Min Act: -0.1700
Data Index: 7558327 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19