Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1437. Min Range: -5.1437
Max Act: 5.1437. Min Act: -0.1700
Data Index: 448375 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1437. Min Range: -5.1437
Max Act: 5.1125. Min Act: -0.1700
Data Index: 474346 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1437. Min Range: -5.1437
Max Act: 5.0812. Min Act: -0.1700
Data Index: 6270966 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1437. Min Range: -5.1437
Max Act: 5.0187. Min Act: -0.1700
Data Index: 6574069 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1437. Min Range: -5.1437
Max Act: 5.0500. Min Act: -0.1700
Data Index: 7099926 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1437. Min Range: -5.1437
Max Act: 5.0187. Min Act: -0.1700
Data Index: 85315 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9562. Min Act: -0.1700
Data Index: 73652 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9562. Min Act: -0.1700
Data Index: 660782 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9562. Min Act: -0.1700
Data Index: 2103296 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9250. Min Act: -0.1700
Data Index: 1484960 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9250. Min Act: -0.1700
Data Index: 4235604 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9250. Min Act: -0.1700
Data Index: 4468381 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9250. Min Act: -0.1700
Data Index: 2383407 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9250. Min Act: -0.1700
Data Index: 2368417 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9250. Min Act: -0.1700
Data Index: 6489244 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.9250. Min Act: -0.1700
Data Index: 4995789 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.8937. Min Act: -0.1700
Data Index: 2602652 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.8937. Min Act: -0.1700
Data Index: 6380594 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.8937. Min Act: -0.1700
Data Index: 1230398 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1437. Min Range: -5.1437
Max Act: 4.8937. Min Act: -0.1700
Data Index: 772513 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19