Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5623 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2612. Min Range: -4.2612
Max Act: 4.2612. Min Act: -0.1700
Data Index: 7186645 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2612. Min Range: -4.2612
Max Act: 4.1049. Min Act: -0.1700
Data Index: 6512094 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2612. Min Range: -4.2612
Max Act: 4.0424. Min Act: -0.1700
Data Index: 3516304 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2612. Min Range: -4.2612
Max Act: 4.0112. Min Act: -0.1700
Data Index: 8532484 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.9174. Min Act: -0.1700
Data Index: 2788538 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8861. Min Act: -0.1700
Data Index: 6282536 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8861. Min Act: -0.1700
Data Index: 5442592 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.9017. Min Act: -0.1700
Data Index: 6034634 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8548. Min Act: -0.1700
Data Index: 7716343 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8079. Min Act: -0.1700
Data Index: 2774992 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.8079. Min Act: -0.1700
Data Index: 353854 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.7766. Min Act: -0.1700
Data Index: 4123803 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.7923. Min Act: -0.1700
Data Index: 4570776 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.7454. Min Act: -0.1700
Data Index: 4832590 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.7297. Min Act: -0.1700
Data Index: 1065172 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.7297. Min Act: -0.1700
Data Index: 4225652 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.7141. Min Act: -0.1700
Data Index: 111188 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.7141. Min Act: -0.1700
Data Index: 6505326 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.6828. Min Act: -0.1700
Data Index: 2478545 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2612. Min Range: -4.2612
Max Act: 3.6828. Min Act: -0.1700
Data Index: 5349539 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19