Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4200 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.9702. Min Act: -0.1700
Data Index: 408611 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.9702. Min Act: -0.1700
Data Index: 6314509 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.8452. Min Act: -0.1700
Data Index: 5239256 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.7202. Min Act: -0.1700
Data Index: 7201812 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.4390. Min Act: -0.1700
Data Index: 8563715 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.4077. Min Act: -0.1700
Data Index: 285596 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.3765. Min Act: -0.1700
Data Index: 5664156 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.2515. Min Act: -0.1700
Data Index: 2522525 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1890. Min Act: -0.1700
Data Index: 6550985 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1890. Min Act: -0.1700
Data Index: 7846961 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1890. Min Act: -0.1700
Data Index: 2642661 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1890. Min Act: -0.1700
Data Index: 4447073 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1577. Min Act: -0.1700
Data Index: 7163817 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1265. Min Act: -0.1700
Data Index: 4693653 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1265. Min Act: -0.1700
Data Index: 6191065 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1265. Min Act: -0.1700
Data Index: 3851940 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1265. Min Act: -0.1700
Data Index: 4519632 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.1265. Min Act: -0.1700
Data Index: 8587351 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.0952. Min Act: -0.1700
Data Index: 6054598 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9702. Min Range: -6.9702
Max Act: 6.0952. Min Act: -0.1700
Data Index: 2997094 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19