Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4664 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0621. Min Range: -6.0621
Max Act: 6.0621. Min Act: -0.1700
Data Index: 3824540 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.7809. Min Act: -0.1700
Data Index: 3973611 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.7496. Min Act: -0.1700
Data Index: 4699650 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.7184. Min Act: -0.1700
Data Index: 3014503 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.7184. Min Act: -0.1700
Data Index: 2846730 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6871. Min Act: -0.1700
Data Index: 3822523 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.7184. Min Act: -0.1700
Data Index: 5705338 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6871. Min Act: -0.1700
Data Index: 5522377 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6559. Min Act: -0.1700
Data Index: 2737832 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6559. Min Act: -0.1700
Data Index: 166916 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6559. Min Act: -0.1700
Data Index: 3086213 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.6246. Min Act: -0.1700
Data Index: 244771 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5934. Min Act: -0.1700
Data Index: 3921799 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5621. Min Act: -0.1700
Data Index: 8721067 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5621. Min Act: -0.1700
Data Index: 8085338 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5934. Min Act: -0.1700
Data Index: 7400714 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5621. Min Act: -0.1700
Data Index: 1557404 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5309. Min Act: -0.1700
Data Index: 2354452 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5621. Min Act: -0.1700
Data Index: 5267538 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0621. Min Range: -6.0621
Max Act: 5.5934. Min Act: -0.1700
Data Index: 2031534 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19