Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1093 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.9721. Min Act: -0.1700
Data Index: 825915 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.8783. Min Act: -0.1700
Data Index: 3318320 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.8783. Min Act: -0.1700
Data Index: 6332726 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.8783. Min Act: -0.1700
Data Index: 4982249 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.8471. Min Act: -0.1700
Data Index: 7049345 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.8471. Min Act: -0.1700
Data Index: 369863 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.8471. Min Act: -0.1700
Data Index: 5508685 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.8471. Min Act: -0.1700
Data Index: 5050154 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.7846. Min Act: -0.1700
Data Index: 4061333 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.7221. Min Act: -0.1700
Data Index: 3488361 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.7221. Min Act: -0.1700
Data Index: 914401 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.7221. Min Act: -0.1700
Data Index: 7761648 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.6908. Min Act: -0.1700
Data Index: 5853358 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.6596. Min Act: -0.1700
Data Index: 251271 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.6908. Min Act: -0.1700
Data Index: 182117 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.6596. Min Act: -0.1700
Data Index: 5254347 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.6283. Min Act: -0.1700
Data Index: 2126354 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.6283. Min Act: -0.1700
Data Index: 1904326 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.6283. Min Act: -0.1700
Data Index: 4264083 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9721. Min Range: -5.9721
Max Act: 5.6283. Min Act: -0.1700
Data Index: 4906238 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19