Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2528. Min Range: -3.2528
Max Act: 3.2528. Min Act: -0.1700
Data Index: 7864401 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2528. Min Range: -3.2528
Max Act: 3.2371. Min Act: -0.1700
Data Index: 7703301 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2528. Min Range: -3.2528
Max Act: 3.1427. Min Act: -0.1700
Data Index: 89110 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2528. Min Range: -3.2528
Max Act: 3.0955. Min Act: -0.1700
Data Index: 8204893 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2528. Min Range: -3.2528
Max Act: 3.0955. Min Act: -0.1700
Data Index: 6618302 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9533. Min Act: -0.1700
Data Index: 7566878 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9850. Min Act: -0.1700
Data Index: 4918921 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9533. Min Act: -0.1700
Data Index: 4868415 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9691. Min Act: -0.1700
Data Index: 5776736 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9691. Min Act: -0.1700
Data Index: 7820643 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9375. Min Act: -0.1700
Data Index: 6781619 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9691. Min Act: -0.1700
Data Index: 516661 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9375. Min Act: -0.1700
Data Index: 87936 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9533. Min Act: -0.1700
Data Index: 5981725 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9216. Min Act: -0.1700
Data Index: 8692322 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9375. Min Act: -0.1700
Data Index: 7539934 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9691. Min Act: -0.1700
Data Index: 3180556 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9216. Min Act: -0.1700
Data Index: 3854021 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9375. Min Act: -0.1700
Data Index: 4307931 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2528. Min Range: -3.2528
Max Act: 2.9216. Min Act: -0.1700
Data Index: 746626 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19