Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3812 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.9514. Min Act: -0.1700
Data Index: 8761160 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.9514. Min Act: -0.1700
Data Index: 79901 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.9514. Min Act: -0.1700
Data Index: 79899 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.8889. Min Act: -0.1700
Data Index: 7563074 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.8577. Min Act: -0.1700
Data Index: 2592178 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.8577. Min Act: -0.1700
Data Index: 6895973 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.8264. Min Act: -0.1700
Data Index: 636779 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7952. Min Act: -0.1700
Data Index: 4537817 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7952. Min Act: -0.1700
Data Index: 8818278 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7639. Min Act: -0.1700
Data Index: 79900 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7639. Min Act: -0.1700
Data Index: 4306370 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7952. Min Act: -0.1700
Data Index: 4851738 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7327. Min Act: -0.1700
Data Index: 5073857 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7327. Min Act: -0.1700
Data Index: 4226867 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7327. Min Act: -0.1700
Data Index: 8011436 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7327. Min Act: -0.1700
Data Index: 7466366 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7327. Min Act: -0.1700
Data Index: 1400021 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7014. Min Act: -0.1700
Data Index: 4872314 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7014. Min Act: -0.1700
Data Index: 2646470 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9514. Min Range: -4.9514
Max Act: 4.7327. Min Act: -0.1700
Data Index: 1402326 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19