Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6150 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.4507. Min Act: -0.1700
Data Index: 2397943 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.4507. Min Act: -0.1700
Data Index: 3611287 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.3257. Min Act: -0.1700
Data Index: 3247407 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2945. Min Act: -0.1700
Data Index: 2414359 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2632. Min Act: -0.1700
Data Index: 5599036 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2632. Min Act: -0.1700
Data Index: 8659337 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2320. Min Act: -0.1700
Data Index: 4327609 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2320. Min Act: -0.1700
Data Index: 5443813 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2320. Min Act: -0.1700
Data Index: 4074375 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2320. Min Act: -0.1700
Data Index: 6718545 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2007. Min Act: -0.1700
Data Index: 8737409 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2007. Min Act: -0.1700
Data Index: 354747 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2007. Min Act: -0.1700
Data Index: 2598865 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2007. Min Act: -0.1700
Data Index: 1275785 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.2007. Min Act: -0.1700
Data Index: 1177502 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.1695. Min Act: -0.1700
Data Index: 921395 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.1382. Min Act: -0.1700
Data Index: 2494194 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.1695. Min Act: -0.1700
Data Index: 2161567 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.1695. Min Act: -0.1700
Data Index: 2327098 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4507. Min Range: -4.4507
Max Act: 4.1695. Min Act: -0.1700
Data Index: 4968336 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19