Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1594 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1732. Min Range: -5.1732
Max Act: 5.1732. Min Act: -0.1700
Data Index: 5108723 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1732. Min Range: -5.1732
Max Act: 5.0794. Min Act: -0.1700
Data Index: 913740 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.8607. Min Act: -0.1700
Data Index: 1770413 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.8607. Min Act: -0.1700
Data Index: 1346274 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.8294. Min Act: -0.1700
Data Index: 3813000 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7982. Min Act: -0.1700
Data Index: 2522864 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.8294. Min Act: -0.1700
Data Index: 6851887 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7982. Min Act: -0.1700
Data Index: 5835296 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7982. Min Act: -0.1700
Data Index: 88733 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7982. Min Act: -0.1700
Data Index: 8130315 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7982. Min Act: -0.1700
Data Index: 5820406 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7357. Min Act: -0.1700
Data Index: 4934501 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7357. Min Act: -0.1700
Data Index: 511309 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7044. Min Act: -0.1700
Data Index: 618980 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7044. Min Act: -0.1700
Data Index: 1622520 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7044. Min Act: -0.1700
Data Index: 4197384 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7044. Min Act: -0.1700
Data Index: 7567325 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.7044. Min Act: -0.1700
Data Index: 1984289 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.6731. Min Act: -0.1700
Data Index: 3116683 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1732. Min Range: -5.1732
Max Act: 4.6731. Min Act: -0.1700
Data Index: 5802498 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19