Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.7023. Min Act: -0.1700
Data Index: 350811 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.6086. Min Act: -0.1700
Data Index: 6076273 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.4523. Min Act: -0.1700
Data Index: 4162700 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.3898. Min Act: -0.1700
Data Index: 7797659 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.3586. Min Act: -0.1700
Data Index: 2914698 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.3586. Min Act: -0.1700
Data Index: 7983072 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.2961. Min Act: -0.1700
Data Index: 5315682 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.2961. Min Act: -0.1700
Data Index: 8681430 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.2336. Min Act: -0.1700
Data Index: 1249624 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.1711. Min Act: -0.1700
Data Index: 8668520 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.1711. Min Act: -0.1700
Data Index: 4007038 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.1711. Min Act: -0.1700
Data Index: 143185 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.1398. Min Act: -0.1700
Data Index: 5408609 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.1398. Min Act: -0.1700
Data Index: 7287041 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.1086. Min Act: -0.1700
Data Index: 2469456 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.0773. Min Act: -0.1700
Data Index: 7063462 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.0773. Min Act: -0.1700
Data Index: 1556687 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.0773. Min Act: -0.1700
Data Index: 2034395 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.0461. Min Act: -0.1700
Data Index: 8470989 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7023. Min Range: -7.7023
Max Act: 7.0148. Min Act: -0.1700
Data Index: 7028490 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19