Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.4978. Min Act: -0.1700
Data Index: 4557041 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.4978. Min Act: -0.1700
Data Index: 2105354 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.4666. Min Act: -0.1700
Data Index: 6286507 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.4353. Min Act: -0.1700
Data Index: 1449350 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.3728. Min Act: -0.1700
Data Index: 4744930 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.3728. Min Act: -0.1700
Data Index: 7261012 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.3416. Min Act: -0.1700
Data Index: 2986440 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.3728. Min Act: -0.1700
Data Index: 7714763 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.3416. Min Act: -0.1700
Data Index: 3743968 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.3103. Min Act: -0.1700
Data Index: 250575 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2791. Min Act: -0.1700
Data Index: 6708473 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2791. Min Act: -0.1700
Data Index: 3400749 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2791. Min Act: -0.1700
Data Index: 8752397 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2791. Min Act: -0.1700
Data Index: 1951200 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2478. Min Act: -0.1700
Data Index: 20860 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2478. Min Act: -0.1700
Data Index: 5473752 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2791. Min Act: -0.1700
Data Index: 218973 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2478. Min Act: -0.1700
Data Index: 4197501 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2478. Min Act: -0.1700
Data Index: 1653877 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4978. Min Range: -4.4978
Max Act: 4.2166. Min Act: -0.1700
Data Index: 1312532 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19