Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1561 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.7674. Min Act: -0.1700
Data Index: 683680 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.7205. Min Act: -0.1700
Data Index: 3336973 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.7048. Min Act: -0.1700
Data Index: 1288917 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.7205. Min Act: -0.1700
Data Index: 8018957 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.6579. Min Act: -0.1700
Data Index: 3342521 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.6579. Min Act: -0.1700
Data Index: 5925556 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.6266. Min Act: -0.1700
Data Index: 960330 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.6110. Min Act: -0.1700
Data Index: 3011766 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.6266. Min Act: -0.1700
Data Index: 1916234 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5953. Min Act: -0.1700
Data Index: 6390578 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5797. Min Act: -0.1700
Data Index: 8658835 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5953. Min Act: -0.1700
Data Index: 6835635 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5797. Min Act: -0.1700
Data Index: 4407285 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5953. Min Act: -0.1700
Data Index: 3796971 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.6110. Min Act: -0.1700
Data Index: 1980451 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5797. Min Act: -0.1700
Data Index: 6748445 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5640. Min Act: -0.1700
Data Index: 7706548 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5640. Min Act: -0.1700
Data Index: 5456929 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5640. Min Act: -0.1700
Data Index: 5612038 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7674. Min Range: -3.7674
Max Act: 3.5640. Min Act: -0.1700
Data Index: 8572827 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19