Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3780. Min Range: -6.3780
Max Act: 6.3780. Min Act: -0.1700
Data Index: 4490459 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3780. Min Range: -6.3780
Max Act: 6.2218. Min Act: -0.1700
Data Index: 3764403 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3780. Min Range: -6.3780
Max Act: 6.1280. Min Act: -0.1700
Data Index: 1858364 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3780. Min Range: -6.3780
Max Act: 6.1280. Min Act: -0.1700
Data Index: 4218083 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3780. Min Range: -6.3780
Max Act: 6.0968. Min Act: -0.1700
Data Index: 1933224 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3780. Min Range: -6.3780
Max Act: 6.0655. Min Act: -0.1700
Data Index: 1875316 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3780. Min Range: -6.3780
Max Act: 6.0343. Min Act: -0.1700
Data Index: 2407813 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9718. Min Act: -0.1700
Data Index: 1557703 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9718. Min Act: -0.1700
Data Index: 4274609 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9718. Min Act: -0.1700
Data Index: 6405505 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3780. Min Range: -6.3780
Max Act: 6.0030. Min Act: -0.1700
Data Index: 2672310 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9405. Min Act: -0.1700
Data Index: 7129100 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9718. Min Act: -0.1700
Data Index: 5551697 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9405. Min Act: -0.1700
Data Index: 2268802 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9405. Min Act: -0.1700
Data Index: 3601603 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9405. Min Act: -0.1700
Data Index: 5935619 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9405. Min Act: -0.1700
Data Index: 7877449 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.9093. Min Act: -0.1700
Data Index: 7830391 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.8780. Min Act: -0.1700
Data Index: 1418799 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3780. Min Range: -6.3780
Max Act: 5.8780. Min Act: -0.1700
Data Index: 2584071 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19