Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 222 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.8446. Min Act: -0.1700
Data Index: 38314 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.8759. Min Act: -0.1700
Data Index: 3817847 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.6571. Min Act: -0.1700
Data Index: 1884893 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.6571. Min Act: -0.1700
Data Index: 4856421 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.6259. Min Act: -0.1700
Data Index: 2864692 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5946. Min Act: -0.1700
Data Index: 8222974 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5946. Min Act: -0.1700
Data Index: 5077477 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.6259. Min Act: -0.1700
Data Index: 6471146 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5946. Min Act: -0.1700
Data Index: 3444814 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5634. Min Act: -0.1700
Data Index: 54476 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5634. Min Act: -0.1700
Data Index: 8518777 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5946. Min Act: -0.1700
Data Index: 2750437 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5321. Min Act: -0.1700
Data Index: 7836692 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5321. Min Act: -0.1700
Data Index: 38315 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5634. Min Act: -0.1700
Data Index: 848480 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5321. Min Act: -0.1700
Data Index: 5161066 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5321. Min Act: -0.1700
Data Index: 1301327 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5009. Min Act: -0.1700
Data Index: 7003699 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.5009. Min Act: -0.1700
Data Index: 4951511 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8759. Min Range: -5.8759
Max Act: 5.4696. Min Act: -0.1700
Data Index: 2197971 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19