Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 175 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.6250. Min Act: -0.1700
Data Index: 4647163 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.4688. Min Act: -0.1700
Data Index: 98436 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.4375. Min Act: -0.1700
Data Index: 8814731 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.4063. Min Act: -0.1700
Data Index: 2693282 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.4688. Min Act: -0.1700
Data Index: 2422691 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1659083 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.4063. Min Act: -0.1700
Data Index: 5169167 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.3750. Min Act: -0.1700
Data Index: 7787377 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.3437. Min Act: -0.1700
Data Index: 8266094 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.3437. Min Act: -0.1700
Data Index: 8792801 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.3125. Min Act: -0.1700
Data Index: 6953796 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.3125. Min Act: -0.1700
Data Index: 4848380 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.3125. Min Act: -0.1700
Data Index: 4690864 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.2812. Min Act: -0.1700
Data Index: 2422693 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.2500. Min Act: -0.1700
Data Index: 212403 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.2500. Min Act: -0.1700
Data Index: 5628566 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.2500. Min Act: -0.1700
Data Index: 2422692 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.2500. Min Act: -0.1700
Data Index: 8440131 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.2500. Min Act: -0.1700
Data Index: 4369723 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6250. Min Range: -4.6250
Max Act: 4.2187. Min Act: -0.1700
Data Index: 6060858 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19