Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1417 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0890. Min Range: -5.0890
Max Act: 5.0890. Min Act: -0.1700
Data Index: 2240624 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.6827. Min Act: -0.1700
Data Index: 4403336 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.6202. Min Act: -0.1700
Data Index: 2558584 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.6202. Min Act: -0.1700
Data Index: 8179661 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.5890. Min Act: -0.1700
Data Index: 6125409 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.5890. Min Act: -0.1700
Data Index: 4971142 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.5890. Min Act: -0.1700
Data Index: 4599583 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.5577. Min Act: -0.1700
Data Index: 2214585 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.5577. Min Act: -0.1700
Data Index: 18887 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.5265. Min Act: -0.1700
Data Index: 1262584 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.5265. Min Act: -0.1700
Data Index: 8017637 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.5265. Min Act: -0.1700
Data Index: 4596389 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.4952. Min Act: -0.1700
Data Index: 5340968 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.4640. Min Act: -0.1700
Data Index: 3280215 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.5265. Min Act: -0.1700
Data Index: 1880556 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.4952. Min Act: -0.1700
Data Index: 6376732 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.4640. Min Act: -0.1700
Data Index: 7022301 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.4640. Min Act: -0.1700
Data Index: 5803104 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.4327. Min Act: -0.1700
Data Index: 6022833 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0890. Min Range: -5.0890
Max Act: 4.4640. Min Act: -0.1700
Data Index: 6526605 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19