Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.9575. Min Act: -0.1700
Data Index: 516724 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.9262. Min Act: -0.1700
Data Index: 7098669 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.9575. Min Act: -0.1700
Data Index: 6127099 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.9262. Min Act: -0.1700
Data Index: 4750623 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.8637. Min Act: -0.1700
Data Index: 7687110 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.8325. Min Act: -0.1700
Data Index: 3741204 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.8012. Min Act: -0.1700
Data Index: 5567326 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.8012. Min Act: -0.1700
Data Index: 2902472 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.8012. Min Act: -0.1700
Data Index: 3289119 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.8012. Min Act: -0.1700
Data Index: 415004 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.7700. Min Act: -0.1700
Data Index: 2659675 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.7700. Min Act: -0.1700
Data Index: 2219771 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.7387. Min Act: -0.1700
Data Index: 5803623 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.7387. Min Act: -0.1700
Data Index: 4359686 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.7075. Min Act: -0.1700
Data Index: 4859325 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.7075. Min Act: -0.1700
Data Index: 7983812 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.6762. Min Act: -0.1700
Data Index: 1584497 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.6762. Min Act: -0.1700
Data Index: 3320931 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.6762. Min Act: -0.1700
Data Index: 4436165 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9575. Min Range: -5.9575
Max Act: 5.7075. Min Act: -0.1700
Data Index: 8003323 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19