Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5909 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.4875. Min Act: -0.1700
Data Index: 707790 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.4250. Min Act: -0.1700
Data Index: 4216968 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.3625. Min Act: -0.1700
Data Index: 1413947 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.3625. Min Act: -0.1700
Data Index: 2766098 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.3625. Min Act: -0.1700
Data Index: 6777531 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.3312. Min Act: -0.1700
Data Index: 3081414 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.3312. Min Act: -0.1700
Data Index: 3427327 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.3000. Min Act: -0.1700
Data Index: 1731152 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.3000. Min Act: -0.1700
Data Index: 6399509 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.2687. Min Act: -0.1700
Data Index: 6792271 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.3000. Min Act: -0.1700
Data Index: 8106354 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.2062. Min Act: -0.1700
Data Index: 5561539 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.2375. Min Act: -0.1700
Data Index: 8307955 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.2375. Min Act: -0.1700
Data Index: 2787977 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.1437. Min Act: -0.1700
Data Index: 8107921 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.1750. Min Act: -0.1700
Data Index: 3348649 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.1437. Min Act: -0.1700
Data Index: 758651 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.1437. Min Act: -0.1700
Data Index: 503212 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.1125. Min Act: -0.1700
Data Index: 8372327 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4875. Min Range: -7.4875
Max Act: 7.1125. Min Act: -0.1700
Data Index: 7187077 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19