Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4523 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1504. Min Range: -6.1504
Max Act: 6.1504. Min Act: -0.1700
Data Index: 1379320 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1504. Min Range: -6.1504
Max Act: 6.0566. Min Act: -0.1700
Data Index: 7954019 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9941. Min Act: -0.1700
Data Index: 3142586 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9941. Min Act: -0.1700
Data Index: 4155968 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9941. Min Act: -0.1700
Data Index: 402200 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9941. Min Act: -0.1700
Data Index: 6770839 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9629. Min Act: -0.1700
Data Index: 2534523 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9629. Min Act: -0.1700
Data Index: 5397363 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9629. Min Act: -0.1700
Data Index: 3314815 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9316. Min Act: -0.1700
Data Index: 824798 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9004. Min Act: -0.1700
Data Index: 7030896 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.9316. Min Act: -0.1700
Data Index: 3520537 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.8691. Min Act: -0.1700
Data Index: 875624 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.8691. Min Act: -0.1700
Data Index: 1765987 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.8691. Min Act: -0.1700
Data Index: 3846551 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.8379. Min Act: -0.1700
Data Index: 2894200 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.8066. Min Act: -0.1700
Data Index: 8495257 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.8066. Min Act: -0.1700
Data Index: 8194957 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.8379. Min Act: -0.1700
Data Index: 6424951 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1504. Min Range: -6.1504
Max Act: 5.8066. Min Act: -0.1700
Data Index: 947100 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19