Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1696
Data Index: 536751 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1654
Data Index: 1243194 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1665
Data Index: 1273474 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1700
Data Index: 6098933 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1664
Data Index: 1967615 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1700
Data Index: 2877676 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1642
Data Index: 3238219 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1698
Data Index: 6980006 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1644
Data Index: 7238952 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1687
Data Index: 4700988 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1694
Data Index: 3665726 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1700
Data Index: 3875838 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.5106. Min Act: -0.1700
Data Index: 4162440 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.4955. Min Act: -0.1700
Data Index: 6851589 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.4881. Min Act: -0.1696
Data Index: 5751340 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.4366. Min Act: -0.1700
Data Index: 4565655 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.4294. Min Act: -0.1700
Data Index: 7325155 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.4151. Min Act: -0.1700
Data Index: 4408461 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.4080. Min Act: -0.1700
Data Index: 8318803 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5106. Min Range: -0.5106
Max Act: 0.3938. Min Act: -0.1700
Data Index: 3570137 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19