Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3396. Min Range: -7.3396
Max Act: 7.3396. Min Act: -0.1700
Data Index: 7223709 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3396. Min Range: -7.3396
Max Act: 7.0896. Min Act: -0.1700
Data Index: 2320518 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.9646. Min Act: -0.1700
Data Index: 1532150 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.9646. Min Act: -0.1700
Data Index: 8209096 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.9333. Min Act: -0.1700
Data Index: 7574715 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.8396. Min Act: -0.1700
Data Index: 3007325 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.7458. Min Act: -0.1700
Data Index: 2320519 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.7146. Min Act: -0.1700
Data Index: 7287374 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6833. Min Act: -0.1700
Data Index: 63221 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6521. Min Act: -0.1700
Data Index: 4151667 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6521. Min Act: -0.1700
Data Index: 7230896 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6521. Min Act: -0.1700
Data Index: 2825618 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6521. Min Act: -0.1700
Data Index: 5141588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6208. Min Act: -0.1700
Data Index: 4304750 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6208. Min Act: -0.1700
Data Index: 6056918 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6208. Min Act: -0.1700
Data Index: 3710658 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6208. Min Act: -0.1700
Data Index: 6379882 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.5896. Min Act: -0.1700
Data Index: 7264679 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.6208. Min Act: -0.1700
Data Index: 7904990 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3396. Min Range: -7.3396
Max Act: 6.5583. Min Act: -0.1700
Data Index: 235707 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19