Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.9267. Min Act: -0.1700
Data Index: 7713669 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.8954. Min Act: -0.1700
Data Index: 6154366 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7704. Min Act: -0.1700
Data Index: 4715941 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7704. Min Act: -0.1700
Data Index: 8126160 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.8017. Min Act: -0.1700
Data Index: 3439386 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 7878890 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 1745588 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 7761290 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 5428410 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 2296930 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7392. Min Act: -0.1700
Data Index: 7751380 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7079. Min Act: -0.1700
Data Index: 1555197 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7079. Min Act: -0.1700
Data Index: 5473373 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7079. Min Act: -0.1700
Data Index: 6153526 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7079. Min Act: -0.1700
Data Index: 3514881 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7079. Min Act: -0.1700
Data Index: 2670864 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7079. Min Act: -0.1700
Data Index: 6754593 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7079. Min Act: -0.1700
Data Index: 6789451 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7079. Min Act: -0.1700
Data Index: 5493017 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9267. Min Range: -5.9267
Max Act: 5.7079. Min Act: -0.1700
Data Index: 4138212 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19