Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2732 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0910. Min Range: -7.0910
Max Act: 7.0910. Min Act: -0.1700
Data Index: 5707907 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0910. Min Range: -7.0910
Max Act: 7.0597. Min Act: -0.1700
Data Index: 4852393 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0910. Min Range: -7.0910
Max Act: 7.0597. Min Act: -0.1700
Data Index: 8198003 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.8722. Min Act: -0.1700
Data Index: 2713661 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.7160. Min Act: -0.1700
Data Index: 5250503 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.6535. Min Act: -0.1700
Data Index: 2002266 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.6535. Min Act: -0.1700
Data Index: 7191555 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.6535. Min Act: -0.1700
Data Index: 2764746 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.6222. Min Act: -0.1700
Data Index: 2617009 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.5597. Min Act: -0.1700
Data Index: 4837304 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.5597. Min Act: -0.1700
Data Index: 1153200 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.5597. Min Act: -0.1700
Data Index: 3620628 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.5285. Min Act: -0.1700
Data Index: 498328 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.5597. Min Act: -0.1700
Data Index: 8749808 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.5285. Min Act: -0.1700
Data Index: 8073678 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.4972. Min Act: -0.1700
Data Index: 7040189 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.4660. Min Act: -0.1700
Data Index: 2232846 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.4660. Min Act: -0.1700
Data Index: 8585702 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.4660. Min Act: -0.1700
Data Index: 8519803 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0910. Min Range: -7.0910
Max Act: 6.4347. Min Act: -0.1700
Data Index: 2550231 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19