Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.7715. Min Act: -0.1700
Data Index: 68698 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.5681. Min Act: -0.1700
Data Index: 6645052 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.5525. Min Act: -0.1700
Data Index: 6269812 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.4898. Min Act: -0.1699
Data Index: 3851589 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.4428. Min Act: -0.1700
Data Index: 5573125 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.3958. Min Act: -0.1700
Data Index: 5689217 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.3801. Min Act: -0.1700
Data Index: 322992 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.3801. Min Act: -0.1700
Data Index: 2491508 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.3488. Min Act: -0.1700
Data Index: 3202298 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.2388. Min Act: -0.1700
Data Index: 933640 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.2231. Min Act: -0.1700
Data Index: 6345308 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.1917. Min Act: -0.1700
Data Index: 7255412 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.2074. Min Act: -0.1700
Data Index: 8825305 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.2074. Min Act: -0.1700
Data Index: 3618553 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.1760. Min Act: -0.1700
Data Index: 7594294 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.1602. Min Act: -0.1700
Data Index: 6837492 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.1445. Min Act: -0.1700
Data Index: 5004254 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.1445. Min Act: -0.1700
Data Index: 5577041 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.1445. Min Act: -0.1700
Data Index: 2748591 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7715. Min Range: -3.7715
Max Act: 3.1445. Min Act: -0.1700
Data Index: 180716 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19