Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4999 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.4614. Min Act: -0.1700
Data Index: 7420072 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.4301. Min Act: -0.1700
Data Index: 2319168 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.3051. Min Act: -0.1700
Data Index: 6852526 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.2739. Min Act: -0.1700
Data Index: 8696546 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.2739. Min Act: -0.1700
Data Index: 5553425 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1801. Min Act: -0.1700
Data Index: 50812 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1489. Min Act: -0.1700
Data Index: 3405605 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1176. Min Act: -0.1700
Data Index: 6910313 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0864. Min Act: -0.1700
Data Index: 943629 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1176. Min Act: -0.1700
Data Index: 7471719 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1489. Min Act: -0.1700
Data Index: 3265726 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0551. Min Act: -0.1700
Data Index: 3558936 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0864. Min Act: -0.1700
Data Index: 3624813 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1176. Min Act: -0.1700
Data Index: 7643072 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0864. Min Act: -0.1700
Data Index: 4465381 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0551. Min Act: -0.1700
Data Index: 8794750 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0551. Min Act: -0.1700
Data Index: 4808644 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0551. Min Act: -0.1700
Data Index: 1630811 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0864. Min Act: -0.1700
Data Index: 800161 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0864. Min Act: -0.1700
Data Index: 7991851 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19