Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.3957. Min Act: -0.1700
Data Index: 1000392 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.3330. Min Act: -0.1700
Data Index: 700182 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.3016. Min Act: -0.1700
Data Index: 2137115 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.2702. Min Act: -0.1700
Data Index: 8249082 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.2387. Min Act: -0.1700
Data Index: 6441905 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.2230. Min Act: -0.1700
Data Index: 6105448 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.2230. Min Act: -0.1700
Data Index: 5658956 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.2073. Min Act: -0.1700
Data Index: 643976 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.2073. Min Act: -0.1700
Data Index: 2076323 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.1916. Min Act: -0.1700
Data Index: 1779012 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.1916. Min Act: -0.1700
Data Index: 4611062 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.1759. Min Act: -0.1700
Data Index: 8259059 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.1759. Min Act: -0.1700
Data Index: 2291665 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.1444. Min Act: -0.1700
Data Index: 6130561 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.1129. Min Act: -0.1700
Data Index: 6259571 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.1129. Min Act: -0.1700
Data Index: 7296612 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.0971. Min Act: -0.1700
Data Index: 3806359 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.0814. Min Act: -0.1700
Data Index: 5513084 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.0971. Min Act: -0.1700
Data Index: 7892220 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3957. Min Range: -3.3957
Max Act: 3.0814. Min Act: -0.1700
Data Index: 864683 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19