Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3821 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.3116. Min Act: -0.1700
Data Index: 475289 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.2803. Min Act: -0.1700
Data Index: 5337108 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.1866. Min Act: -0.1700
Data Index: 2535276 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.1553. Min Act: -0.1700
Data Index: 435083 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.1553. Min Act: -0.1700
Data Index: 4049078 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0928. Min Act: -0.1700
Data Index: 4923741 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.1241. Min Act: -0.1700
Data Index: 302357 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.1553. Min Act: -0.1700
Data Index: 1122497 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0928. Min Act: -0.1700
Data Index: 2898886 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0928. Min Act: -0.1700
Data Index: 3601955 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0616. Min Act: -0.1700
Data Index: 5155588 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0616. Min Act: -0.1700
Data Index: 2151165 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0928. Min Act: -0.1700
Data Index: 5264085 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0616. Min Act: -0.1700
Data Index: 747236 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0616. Min Act: -0.1700
Data Index: 7734430 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0303. Min Act: -0.1700
Data Index: 6257242 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0303. Min Act: -0.1700
Data Index: 1010760 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0303. Min Act: -0.1700
Data Index: 4933377 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0303. Min Act: -0.1700
Data Index: 7436217 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3116. Min Range: -5.3116
Max Act: 5.0303. Min Act: -0.1700
Data Index: 2636980 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19