Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2489. Min Range: -4.2489
Max Act: 4.2489. Min Act: -0.1700
Data Index: 4714514 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2489. Min Range: -4.2489
Max Act: 4.1083. Min Act: -0.1700
Data Index: 5340618 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2489. Min Range: -4.2489
Max Act: 4.1083. Min Act: -0.1700
Data Index: 3718452 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2489. Min Range: -4.2489
Max Act: 4.0145. Min Act: -0.1700
Data Index: 8493266 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2489. Min Range: -4.2489
Max Act: 4.0145. Min Act: -0.1700
Data Index: 6734580 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9989. Min Act: -0.1700
Data Index: 1971536 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9989. Min Act: -0.1700
Data Index: 2808480 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9520. Min Act: -0.1700
Data Index: 4700903 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9363. Min Act: -0.1700
Data Index: 7432625 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9207. Min Act: -0.1700
Data Index: 8318588 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9207. Min Act: -0.1700
Data Index: 8697604 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9520. Min Act: -0.1700
Data Index: 685316 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9051. Min Act: -0.1700
Data Index: 3825951 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.8894. Min Act: -0.1700
Data Index: 2593377 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9051. Min Act: -0.1700
Data Index: 2497566 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.8738. Min Act: -0.1700
Data Index: 3861737 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.9051. Min Act: -0.1700
Data Index: 2917869 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.8582. Min Act: -0.1700
Data Index: 3189583 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.8738. Min Act: -0.1700
Data Index: 5019986 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2489. Min Range: -4.2489
Max Act: 3.8738. Min Act: -0.1700
Data Index: 7089954 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19