Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 73 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0332. Min Range: -5.0332
Max Act: 5.0332. Min Act: -0.1700
Data Index: 655058 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9707. Min Act: -0.1700
Data Index: 7270159 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9707. Min Act: -0.1700
Data Index: 6570168 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8144. Min Act: -0.1700
Data Index: 3542003 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.8144. Min Act: -0.1700
Data Index: 8812040 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7832. Min Act: -0.1700
Data Index: 2942146 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7519. Min Act: -0.1700
Data Index: 5730806 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7519. Min Act: -0.1700
Data Index: 5389765 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7207. Min Act: -0.1700
Data Index: 6192075 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.7207. Min Act: -0.1700
Data Index: 5115839 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6894. Min Act: -0.1700
Data Index: 8220304 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6894. Min Act: -0.1700
Data Index: 4771921 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6894. Min Act: -0.1700
Data Index: 7284536 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6582. Min Act: -0.1700
Data Index: 7499995 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6582. Min Act: -0.1700
Data Index: 1907535 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6269. Min Act: -0.1700
Data Index: 1526567 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6269. Min Act: -0.1700
Data Index: 5875550 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6269. Min Act: -0.1700
Data Index: 5566564 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6269. Min Act: -0.1700
Data Index: 5288734 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.6269. Min Act: -0.1700
Data Index: 1470029 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19