Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.9410. Min Act: -0.1700
Data Index: 7013354 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.9410. Min Act: -0.1700
Data Index: 7318045 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.9410. Min Act: -0.1700
Data Index: 5457311 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.9098. Min Act: -0.1700
Data Index: 4569802 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8785. Min Act: -0.1700
Data Index: 5354759 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8785. Min Act: -0.1700
Data Index: 4165377 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8785. Min Act: -0.1700
Data Index: 7491527 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8785. Min Act: -0.1700
Data Index: 3348463 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8785. Min Act: -0.1700
Data Index: 7487398 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8785. Min Act: -0.1700
Data Index: 4537784 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8785. Min Act: -0.1700
Data Index: 4335925 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8785. Min Act: -0.1700
Data Index: 8421916 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8473. Min Act: -0.1700
Data Index: 4409708 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8473. Min Act: -0.1700
Data Index: 5370814 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8473. Min Act: -0.1700
Data Index: 4559326 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8473. Min Act: -0.1700
Data Index: 4272048 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8473. Min Act: -0.1700
Data Index: 6069260 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8473. Min Act: -0.1700
Data Index: 2146377 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8785. Min Act: -0.1700
Data Index: 908397 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9410. Min Range: -5.9410
Max Act: 5.8160. Min Act: -0.1700
Data Index: 2146387 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19