Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.8850. Min Act: -0.1700
Data Index: 8680930 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.8850. Min Act: -0.1700
Data Index: 3785988 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.7912. Min Act: -0.1700
Data Index: 7875618 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.6975. Min Act: -0.1700
Data Index: 2786586 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.6037. Min Act: -0.1700
Data Index: 2464534 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.6350. Min Act: -0.1700
Data Index: 7968602 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.6037. Min Act: -0.1700
Data Index: 3359481 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.6037. Min Act: -0.1700
Data Index: 66880 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.5412. Min Act: -0.1700
Data Index: 682339 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.5412. Min Act: -0.1700
Data Index: 4278467 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.4787. Min Act: -0.1700
Data Index: 5671599 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.4787. Min Act: -0.1700
Data Index: 1090865 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.4787. Min Act: -0.1700
Data Index: 5624431 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.4475. Min Act: -0.1700
Data Index: 7444314 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.4787. Min Act: -0.1700
Data Index: 3271904 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.4162. Min Act: -0.1700
Data Index: 2855651 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.4475. Min Act: -0.1700
Data Index: 1750850 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.4162. Min Act: -0.1700
Data Index: 670617 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.4162. Min Act: -0.1700
Data Index: 758860 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8850. Min Range: -5.8850
Max Act: 5.3850. Min Act: -0.1700
Data Index: 1501134 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19