Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.6248. Min Act: -0.1700
Data Index: 5079764 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.6091. Min Act: -0.1700
Data Index: 581773 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.5778. Min Act: -0.1700
Data Index: 5515208 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.5622. Min Act: -0.1700
Data Index: 7902279 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.5308. Min Act: -0.1700
Data Index: 5456482 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.5152. Min Act: -0.1700
Data Index: 373206 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4995. Min Act: -0.1700
Data Index: 4768814 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4995. Min Act: -0.1700
Data Index: 192689 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4839. Min Act: -0.1700
Data Index: 752940 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4682. Min Act: -0.1700
Data Index: 2751574 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4682. Min Act: -0.1700
Data Index: 1443981 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4525. Min Act: -0.1700
Data Index: 4847962 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4368. Min Act: -0.1700
Data Index: 6864028 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4525. Min Act: -0.1700
Data Index: 637290 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4525. Min Act: -0.1700
Data Index: 1995263 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4368. Min Act: -0.1700
Data Index: 4517192 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4368. Min Act: -0.1700
Data Index: 5576187 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4525. Min Act: -0.1700
Data Index: 670492 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4525. Min Act: -0.1700
Data Index: 4123048 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6248. Min Range: -3.6248
Max Act: 3.4055. Min Act: -0.1700
Data Index: 3020013 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19