Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0547. Min Range: -8.0547
Max Act: 8.0547. Min Act: -0.1700
Data Index: 648543 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.6172. Min Act: -0.1700
Data Index: 3802262 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.6172. Min Act: -0.1700
Data Index: 8480185 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.6172. Min Act: -0.1700
Data Index: 8720445 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.4297. Min Act: -0.1700
Data Index: 7114004 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.4297. Min Act: -0.1700
Data Index: 4842912 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.3672. Min Act: -0.1700
Data Index: 4018818 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.3672. Min Act: -0.1700
Data Index: 282910 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.3672. Min Act: -0.1700
Data Index: 4876073 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.3047. Min Act: -0.1700
Data Index: 7348787 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.3047. Min Act: -0.1700
Data Index: 1616242 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.2735. Min Act: -0.1700
Data Index: 884672 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.2422. Min Act: -0.1700
Data Index: 1665131 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.2110. Min Act: -0.1700
Data Index: 6301202 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.1797. Min Act: -0.1700
Data Index: 5761027 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.1797. Min Act: -0.1700
Data Index: 5461404 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.1797. Min Act: -0.1700
Data Index: 5781312 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.1485. Min Act: -0.1700
Data Index: 7405554 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.1172. Min Act: -0.1700
Data Index: 3737457 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0547. Min Range: -8.0547
Max Act: 7.1485. Min Act: -0.1700
Data Index: 385064 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19