Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3793 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.5243. Min Act: -0.1700
Data Index: 3833176 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.4931. Min Act: -0.1700
Data Index: 5955902 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.4306. Min Act: -0.1700
Data Index: 4927739 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.3681. Min Act: -0.1700
Data Index: 2858499 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.3056. Min Act: -0.1700
Data Index: 6313649 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.3368. Min Act: -0.1700
Data Index: 8521788 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.2118. Min Act: -0.1700
Data Index: 5462543 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1493. Min Act: -0.1700
Data Index: 1169943 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1806. Min Act: -0.1700
Data Index: 2143973 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1806. Min Act: -0.1700
Data Index: 5519061 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1181. Min Act: -0.1700
Data Index: 3300723 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1181. Min Act: -0.1700
Data Index: 2936652 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1181. Min Act: -0.1700
Data Index: 6423181 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.0868. Min Act: -0.1700
Data Index: 1430584 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.1181. Min Act: -0.1700
Data Index: 954557 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.0868. Min Act: -0.1700
Data Index: 2594721 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.0868. Min Act: -0.1700
Data Index: 7573970 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.0555. Min Act: -0.1700
Data Index: 3577622 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.0555. Min Act: -0.1700
Data Index: 4528288 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5243. Min Range: -4.5243
Max Act: 4.0555. Min Act: -0.1700
Data Index: 8485544 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19