Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.9483. Min Act: -0.1700
Data Index: 4265415 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.9483. Min Act: -0.1700
Data Index: 5513154 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.8858. Min Act: -0.1700
Data Index: 3250083 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.7608. Min Act: -0.1700
Data Index: 7404792 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.7608. Min Act: -0.1700
Data Index: 908141 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.7608. Min Act: -0.1700
Data Index: 8171600 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.6983. Min Act: -0.1700
Data Index: 7818528 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.6358. Min Act: -0.1700
Data Index: 2905960 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.6358. Min Act: -0.1700
Data Index: 3652072 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.6358. Min Act: -0.1700
Data Index: 2357614 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.6358. Min Act: -0.1700
Data Index: 7404795 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.6358. Min Act: -0.1700
Data Index: 593662 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.5733. Min Act: -0.1700
Data Index: 155463 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.5733. Min Act: -0.1700
Data Index: 4032606 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.5108. Min Act: -0.1700
Data Index: 189502 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.5108. Min Act: -0.1700
Data Index: 4826647 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.5108. Min Act: -0.1700
Data Index: 5749066 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.3858. Min Act: -0.1700
Data Index: 6390859 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.3858. Min Act: -0.1700
Data Index: 209826 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9483. Min Range: -8.9483
Max Act: 8.3858. Min Act: -0.1700
Data Index: 6405881 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19