Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.1932. Min Act: -0.1700
Data Index: 352638 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0987. Min Act: -0.1700
Data Index: 5647738 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0830. Min Act: -0.1700
Data Index: 5228402 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0830. Min Act: -0.1700
Data Index: 2925205 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0672. Min Act: -0.1700
Data Index: 1507904 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0356. Min Act: -0.1700
Data Index: 3748243 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0199. Min Act: -0.1700
Data Index: 8062977 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0041. Min Act: -0.1700
Data Index: 5647734 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0041. Min Act: -0.1700
Data Index: 8491048 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0041. Min Act: -0.1700
Data Index: 5821684 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1932. Min Range: -3.1932
Max Act: 3.0041. Min Act: -0.1700
Data Index: 5335079 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1932. Min Range: -3.1932
Max Act: 2.9882. Min Act: -0.1700
Data Index: 3774579 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1932. Min Range: -3.1932
Max Act: 2.9882. Min Act: -0.1700
Data Index: 2862558 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1932. Min Range: -3.1932
Max Act: 2.9882. Min Act: -0.1700
Data Index: 5021085 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1932. Min Range: -3.1932
Max Act: 2.9882. Min Act: -0.1700
Data Index: 1413228 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1932. Min Range: -3.1932
Max Act: 2.9882. Min Act: -0.1700
Data Index: 7628349 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1932. Min Range: -3.1932
Max Act: 2.9882. Min Act: -0.1700
Data Index: 7949779 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1932. Min Range: -3.1932
Max Act: 2.9882. Min Act: -0.1700
Data Index: 4828457 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1932. Min Range: -3.1932
Max Act: 2.9882. Min Act: -0.1700
Data Index: 6016101 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1932. Min Range: -3.1932
Max Act: 2.9882. Min Act: -0.1700
Data Index: 3257621 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19