Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8898. Min Act: -0.1700
Data Index: 4706066 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8585. Min Act: -0.1700
Data Index: 1575517 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8898. Min Act: -0.1700
Data Index: 7886775 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8741. Min Act: -0.1700
Data Index: 4570930 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8898. Min Act: -0.1700
Data Index: 4374259 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8429. Min Act: -0.1700
Data Index: 3745466 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8585. Min Act: -0.1700
Data Index: 387510 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.9210. Min Act: -0.1700
Data Index: 740740 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8898. Min Act: -0.1700
Data Index: 3732878 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8585. Min Act: -0.1700
Data Index: 6770364 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8585. Min Act: -0.1700
Data Index: 269885 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8585. Min Act: -0.1700
Data Index: 8398384 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8585. Min Act: -0.1700
Data Index: 699339 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8585. Min Act: -0.1700
Data Index: 4410563 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.7960. Min Act: -0.1700
Data Index: 2836081 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8272. Min Act: -0.1700
Data Index: 6012520 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8429. Min Act: -0.1700
Data Index: 6889242 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8116. Min Act: -0.1700
Data Index: 5671849 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8116. Min Act: -0.1700
Data Index: 131352 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9210. Min Range: -3.9210
Max Act: 3.8116. Min Act: -0.1700
Data Index: 20406 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19