Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2994 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.9875. Min Act: -0.1700
Data Index: 2459626 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.7062. Min Act: -0.1700
Data Index: 8785807 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.6437. Min Act: -0.1700
Data Index: 3544950 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.6125. Min Act: -0.1700
Data Index: 3822906 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.6125. Min Act: -0.1700
Data Index: 8271646 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5812. Min Act: -0.1700
Data Index: 3886378 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5812. Min Act: -0.1700
Data Index: 5976333 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5500. Min Act: -0.1700
Data Index: 1693919 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5500. Min Act: -0.1700
Data Index: 3202931 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5500. Min Act: -0.1700
Data Index: 3944010 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5500. Min Act: -0.1700
Data Index: 3370580 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5187. Min Act: -0.1700
Data Index: 5780958 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.5187. Min Act: -0.1700
Data Index: 490190 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4562. Min Act: -0.1700
Data Index: 5475634 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4562. Min Act: -0.1700
Data Index: 5321229 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4250. Min Act: -0.1700
Data Index: 3397118 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.4250. Min Act: -0.1700
Data Index: 7803185 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.3937. Min Act: -0.1700
Data Index: 3179535 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.3937. Min Act: -0.1700
Data Index: 5877633 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9875. Min Range: -5.9875
Max Act: 5.3625. Min Act: -0.1700
Data Index: 7800255 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19