Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.5554. Min Act: -0.1700
Data Index: 876045 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.2742. Min Act: -0.1700
Data Index: 7738016 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.2429. Min Act: -0.1700
Data Index: 1257306 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.2742. Min Act: -0.1700
Data Index: 6527500 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.2429. Min Act: -0.1700
Data Index: 7829871 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.2117. Min Act: -0.1700
Data Index: 4041613 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.2117. Min Act: -0.1700
Data Index: 1897312 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.1804. Min Act: -0.1700
Data Index: 7629675 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.1492. Min Act: -0.1700
Data Index: 5079350 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.1492. Min Act: -0.1700
Data Index: 6219964 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.1179. Min Act: -0.1700
Data Index: 8055371 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.1492. Min Act: -0.1700
Data Index: 3157302 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.1179. Min Act: -0.1700
Data Index: 5865873 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.0867. Min Act: -0.1700
Data Index: 1310755 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.1179. Min Act: -0.1700
Data Index: 5572424 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.1179. Min Act: -0.1700
Data Index: 364821 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.1492. Min Act: -0.1700
Data Index: 528818 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.0554. Min Act: -0.1700
Data Index: 2213974 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.0867. Min Act: -0.1700
Data Index: 73375 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5554. Min Range: -6.5554
Max Act: 6.0867. Min Act: -0.1700
Data Index: 4918035 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19