Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3738 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4332. Min Range: -6.4332
Max Act: 6.4332. Min Act: -0.1700
Data Index: 7166547 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4332. Min Range: -6.4332
Max Act: 6.1519. Min Act: -0.1700
Data Index: 1327250 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4332. Min Range: -6.4332
Max Act: 6.0582. Min Act: -0.1700
Data Index: 5005551 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4332. Min Range: -6.4332
Max Act: 6.0269. Min Act: -0.1700
Data Index: 4845017 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.9957. Min Act: -0.1700
Data Index: 291907 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.9332. Min Act: -0.1700
Data Index: 8513052 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.9019. Min Act: -0.1700
Data Index: 6629603 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.8707. Min Act: -0.1700
Data Index: 3233780 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.8394. Min Act: -0.1700
Data Index: 4890411 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.8707. Min Act: -0.1700
Data Index: 3372813 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.8082. Min Act: -0.1700
Data Index: 7978855 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.8082. Min Act: -0.1700
Data Index: 1202126 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.7769. Min Act: -0.1700
Data Index: 2417569 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.7457. Min Act: -0.1700
Data Index: 3178845 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.7457. Min Act: -0.1700
Data Index: 3342849 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.7457. Min Act: -0.1700
Data Index: 2579329 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.7457. Min Act: -0.1700
Data Index: 6605127 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.7457. Min Act: -0.1700
Data Index: 2794545 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.7144. Min Act: -0.1700
Data Index: 4895781 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4332. Min Range: -6.4332
Max Act: 5.7144. Min Act: -0.1700
Data Index: 4033245 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19