Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2660 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6026. Min Range: -5.6026
Max Act: 5.6026. Min Act: -0.1699
Data Index: 3646414 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6026. Min Range: -5.6026
Max Act: 5.2276. Min Act: -0.1700
Data Index: 8147636 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6026. Min Range: -5.6026
Max Act: 5.2276. Min Act: -0.1700
Data Index: 6657343 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6026. Min Range: -5.6026
Max Act: 5.0089. Min Act: -0.1700
Data Index: 5568714 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.9464. Min Act: -0.1700
Data Index: 4890322 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.9776. Min Act: -0.1700
Data Index: 321328 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.9151. Min Act: -0.1700
Data Index: 2529414 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.9464. Min Act: -0.1700
Data Index: 6693883 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 6391531 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 5024560 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.8526. Min Act: -0.1700
Data Index: 6632144 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 3603380 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.7589. Min Act: -0.1700
Data Index: 6462228 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.7901. Min Act: -0.1700
Data Index: 3646415 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.7276. Min Act: -0.1700
Data Index: 5304536 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.7276. Min Act: -0.1700
Data Index: 4279715 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.6964. Min Act: -0.1643
Data Index: 6159639 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.6964. Min Act: -0.1700
Data Index: 3494804 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.6964. Min Act: -0.1700
Data Index: 5285621 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6026. Min Range: -5.6026
Max Act: 4.6964. Min Act: -0.1700
Data Index: 4727822 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19