Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4381 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1634. Min Range: -7.1634
Max Act: 7.1634. Min Act: -0.1700
Data Index: 904634 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1634. Min Range: -7.1634
Max Act: 7.1009. Min Act: -0.1700
Data Index: 1769365 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1634. Min Range: -7.1634
Max Act: 7.0384. Min Act: -0.1700
Data Index: 3297786 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1634. Min Range: -7.1634
Max Act: 7.0072. Min Act: -0.1700
Data Index: 7881359 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1634. Min Range: -7.1634
Max Act: 7.0072. Min Act: -0.1700
Data Index: 5189654 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1634. Min Range: -7.1634
Max Act: 7.0072. Min Act: -0.1700
Data Index: 4930309 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1634. Min Range: -7.1634
Max Act: 7.0072. Min Act: -0.1700
Data Index: 8016579 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.9759. Min Act: -0.1700
Data Index: 3095155 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.9447. Min Act: -0.1700
Data Index: 8825648 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.9447. Min Act: -0.1700
Data Index: 6498065 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.9447. Min Act: -0.1700
Data Index: 6813397 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.9134. Min Act: -0.1700
Data Index: 6417529 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.9134. Min Act: -0.1700
Data Index: 4074325 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.9134. Min Act: -0.1700
Data Index: 8830733 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.9134. Min Act: -0.1700
Data Index: 4238417 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.8822. Min Act: -0.1700
Data Index: 6314406 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.8822. Min Act: -0.1700
Data Index: 2983058 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.8822. Min Act: -0.1700
Data Index: 2907949 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.8509. Min Act: -0.1700
Data Index: 3070060 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1634. Min Range: -7.1634
Max Act: 6.8509. Min Act: -0.1700
Data Index: 491547 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19