Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0005. Min Range: -7.0005
Max Act: 7.0005. Min Act: -0.1700
Data Index: 4878040 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.9693. Min Act: -0.1700
Data Index: 5605622 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.9380. Min Act: -0.1700
Data Index: 8748008 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.7505. Min Act: -0.1700
Data Index: 4468921 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.7818. Min Act: -0.1700
Data Index: 5626656 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.7505. Min Act: -0.1700
Data Index: 3621511 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.7505. Min Act: -0.1700
Data Index: 1444364 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.6880. Min Act: -0.1700
Data Index: 1819545 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.6880. Min Act: -0.1700
Data Index: 4670802 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.6255. Min Act: -0.1700
Data Index: 3968655 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.6568. Min Act: -0.1700
Data Index: 6229807 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.6255. Min Act: -0.1700
Data Index: 6779976 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.6255. Min Act: -0.1700
Data Index: 2122568 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.5630. Min Act: -0.1700
Data Index: 121608 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.5630. Min Act: -0.1699
Data Index: 5718440 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.5318. Min Act: -0.1700
Data Index: 6741785 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.5318. Min Act: -0.1700
Data Index: 4947571 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.5318. Min Act: -0.1700
Data Index: 4082140 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.5318. Min Act: -0.1700
Data Index: 4733776 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0005. Min Range: -7.0005
Max Act: 6.4693. Min Act: -0.1700
Data Index: 2692155 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19