Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 930 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3081. Min Range: -4.3081
Max Act: 4.3081. Min Act: -0.1700
Data Index: 7319747 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3081. Min Range: -4.3081
Max Act: 4.1518. Min Act: -0.1700
Data Index: 9629 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.9330. Min Act: -0.1700
Data Index: 8403704 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.9330. Min Act: -0.1700
Data Index: 21910 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.9330. Min Act: -0.1700
Data Index: 3309882 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.9017. Min Act: -0.1700
Data Index: 5422452 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.9017. Min Act: -0.1700
Data Index: 1958087 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.9017. Min Act: -0.1700
Data Index: 8296007 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8705. Min Act: -0.1700
Data Index: 3857673 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8705. Min Act: -0.1700
Data Index: 3090952 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8392. Min Act: -0.1700
Data Index: 257667 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8392. Min Act: -0.1700
Data Index: 2593148 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8079. Min Act: -0.1700
Data Index: 7665094 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8079. Min Act: -0.1700
Data Index: 3626637 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8079. Min Act: -0.1700
Data Index: 1034039 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8079. Min Act: -0.1700
Data Index: 1906163 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8079. Min Act: -0.1700
Data Index: 7188504 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8079. Min Act: -0.1700
Data Index: 2037811 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8392. Min Act: -0.1700
Data Index: 2046969 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3081. Min Range: -4.3081
Max Act: 3.8392. Min Act: -0.1700
Data Index: 947451 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19