Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.6316. Min Act: -0.1700
Data Index: 529318 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.5691. Min Act: -0.1700
Data Index: 4232451 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.5066. Min Act: -0.1700
Data Index: 2508982 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3816. Min Act: -0.1700
Data Index: 705570 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3816. Min Act: -0.1700
Data Index: 295842 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3191. Min Act: -0.1700
Data Index: 292921 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3191. Min Act: -0.1700
Data Index: 4832802 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3191. Min Act: -0.1700
Data Index: 3535041 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3191. Min Act: -0.1700
Data Index: 677934 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3191. Min Act: -0.1700
Data Index: 8628944 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3191. Min Act: -0.1700
Data Index: 6813871 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3191. Min Act: -0.1700
Data Index: 5305559 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.2566. Min Act: -0.1700
Data Index: 6734637 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.2566. Min Act: -0.1700
Data Index: 3387489 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.2566. Min Act: -0.1700
Data Index: 5966288 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.2566. Min Act: -0.1700
Data Index: 4493092 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.2566. Min Act: -0.1700
Data Index: 5759525 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.2566. Min Act: -0.1700
Data Index: 1785491 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.3191. Min Act: -0.1700
Data Index: 235108 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6316. Min Range: -8.6316
Max Act: 8.2566. Min Act: -0.1700
Data Index: 1532204 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19