Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 920 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.7281. Min Act: -0.1700
Data Index: 7696970 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.6344. Min Act: -0.1700
Data Index: 7048707 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.6656. Min Act: -0.1700
Data Index: 6168418 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.6344. Min Act: -0.1700
Data Index: 3741930 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.6344. Min Act: -0.1700
Data Index: 144670 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.6031. Min Act: -0.1700
Data Index: 3450752 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.6031. Min Act: -0.1700
Data Index: 5209798 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5719. Min Act: -0.1700
Data Index: 8058424 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5406. Min Act: -0.1700
Data Index: 7690545 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5406. Min Act: -0.1700
Data Index: 7276109 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5406. Min Act: -0.1700
Data Index: 3366486 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5406. Min Act: -0.1700
Data Index: 4415625 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5094. Min Act: -0.1700
Data Index: 1734836 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5094. Min Act: -0.1700
Data Index: 6449637 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5094. Min Act: -0.1700
Data Index: 3575119 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5094. Min Act: -0.1700
Data Index: 2256240 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5094. Min Act: -0.1700
Data Index: 5425087 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5094. Min Act: -0.1700
Data Index: 3790282 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.5406. Min Act: -0.1700
Data Index: 815316 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7281. Min Range: -6.7281
Max Act: 6.4469. Min Act: -0.1700
Data Index: 6041429 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19