Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1966. Min Range: -5.1966
Max Act: 5.1966. Min Act: -0.1700
Data Index: 5145048 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1966. Min Range: -5.1966
Max Act: 5.0716. Min Act: -0.1700
Data Index: 6632217 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1966. Min Range: -5.1966
Max Act: 5.0404. Min Act: -0.1700
Data Index: 2995556 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1966. Min Range: -5.1966
Max Act: 5.0091. Min Act: -0.1700
Data Index: 385223 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.9779. Min Act: -0.1700
Data Index: 858824 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.9779. Min Act: -0.1700
Data Index: 5426575 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.9466. Min Act: -0.1700
Data Index: 3554833 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.9466. Min Act: -0.1700
Data Index: 7570251 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.9154. Min Act: -0.1700
Data Index: 7507395 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.8841. Min Act: -0.1700
Data Index: 7063439 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.8529. Min Act: -0.1700
Data Index: 7550705 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.8529. Min Act: -0.1700
Data Index: 6094899 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.8529. Min Act: -0.1700
Data Index: 1146295 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.8216. Min Act: -0.1700
Data Index: 612727 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.8216. Min Act: -0.1700
Data Index: 7150883 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.8216. Min Act: -0.1700
Data Index: 8616544 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.8216. Min Act: -0.1700
Data Index: 6838227 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.7904. Min Act: -0.1700
Data Index: 3228218 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.7904. Min Act: -0.1700
Data Index: 6353855 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1966. Min Range: -5.1966
Max Act: 4.7904. Min Act: -0.1700
Data Index: 997490 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19