Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4381. Min Range: -8.4381
Max Act: 8.4381. Min Act: -0.1700
Data Index: 5729305 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4381. Min Range: -8.4381
Max Act: 8.1568. Min Act: -0.1700
Data Index: 1965746 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.9068. Min Act: -0.1700
Data Index: 1359047 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.9068. Min Act: -0.1700
Data Index: 3328127 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.8756. Min Act: -0.1700
Data Index: 4725413 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.7506. Min Act: -0.1700
Data Index: 1065365 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.6881. Min Act: -0.1700
Data Index: 4035035 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.6568. Min Act: -0.1700
Data Index: 6022587 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.6256. Min Act: -0.1700
Data Index: 2858722 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.5943. Min Act: -0.1700
Data Index: 1513221 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.5631. Min Act: -0.1700
Data Index: 1389484 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.5943. Min Act: -0.1700
Data Index: 6871245 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.5318. Min Act: -0.1700
Data Index: 3703795 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.4693. Min Act: -0.1700
Data Index: 81357 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.5006. Min Act: -0.1700
Data Index: 1847354 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.4693. Min Act: -0.1700
Data Index: 3542552 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.4068. Min Act: -0.1700
Data Index: 234255 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.4381. Min Act: -0.1700
Data Index: 4276836 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.3443. Min Act: -0.1700
Data Index: 6423015 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4381. Min Range: -8.4381
Max Act: 7.3756. Min Act: -0.1700
Data Index: 234244 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19