Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.8559. Min Act: -0.1700
Data Index: 4273461 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.6684. Min Act: -0.1700
Data Index: 7769718 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.6684. Min Act: -0.1700
Data Index: 1715981 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.6059. Min Act: -0.1700
Data Index: 2850307 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.5434. Min Act: -0.1700
Data Index: 2429265 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.5434. Min Act: -0.1700
Data Index: 1440981 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.4809. Min Act: -0.1700
Data Index: 1563064 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.4809. Min Act: -0.1700
Data Index: 8726969 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.4809. Min Act: -0.1700
Data Index: 8598568 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.4184. Min Act: -0.1700
Data Index: 741685 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.4184. Min Act: -0.1700
Data Index: 8544712 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.3559. Min Act: -0.1700
Data Index: 7204762 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.3559. Min Act: -0.1700
Data Index: 6273774 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.3559. Min Act: -0.1700
Data Index: 7983534 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.3559. Min Act: -0.1700
Data Index: 5682412 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.2934. Min Act: -0.1700
Data Index: 7348055 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.2309. Min Act: -0.1700
Data Index: 4173119 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.2309. Min Act: -0.1700
Data Index: 8690510 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.2309. Min Act: -0.1700
Data Index: 5198971 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8559. Min Range: -8.8559
Max Act: 8.2309. Min Act: -0.1700
Data Index: 741683 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19