Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.8504. Min Act: -0.1700
Data Index: 4200653 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.6941. Min Act: -0.1700
Data Index: 841812 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.5379. Min Act: -0.1700
Data Index: 2032030 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.5066. Min Act: -0.1700
Data Index: 2424152 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.4754. Min Act: -0.1700
Data Index: 2033435 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.4441. Min Act: -0.1700
Data Index: 949453 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.3191. Min Act: -0.1700
Data Index: 8211898 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.2879. Min Act: -0.1700
Data Index: 8684205 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.2566. Min Act: -0.1700
Data Index: 7568841 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.2566. Min Act: -0.1700
Data Index: 795650 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.2566. Min Act: -0.1700
Data Index: 1781162 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.2254. Min Act: -0.1700
Data Index: 7520096 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.1629. Min Act: -0.1700
Data Index: 5458353 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.1316. Min Act: -0.1700
Data Index: 460097 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.1629. Min Act: -0.1700
Data Index: 2905516 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.1629. Min Act: -0.1700
Data Index: 624121 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.1629. Min Act: -0.1700
Data Index: 6847011 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.1316. Min Act: -0.1700
Data Index: 1880501 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.1316. Min Act: -0.1700
Data Index: 697632 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8504. Min Range: -5.8504
Max Act: 5.1316. Min Act: -0.1700
Data Index: 6475358 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19