Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 246 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5713. Min Range: -7.5713
Max Act: 7.5713. Min Act: -0.1700
Data Index: 6642343 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5713. Min Range: -7.5713
Max Act: 7.5088. Min Act: -0.1700
Data Index: 6146364 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5713. Min Range: -7.5713
Max Act: 7.2901. Min Act: -0.1700
Data Index: 1652863 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5713. Min Range: -7.5713
Max Act: 7.1338. Min Act: -0.1700
Data Index: 1143170 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5713. Min Range: -7.5713
Max Act: 7.1338. Min Act: -0.1700
Data Index: 1455008 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5713. Min Range: -7.5713
Max Act: 7.0401. Min Act: -0.1700
Data Index: 6039755 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5713. Min Range: -7.5713
Max Act: 7.0401. Min Act: -0.1700
Data Index: 759336 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5713. Min Range: -7.5713
Max Act: 7.0401. Min Act: -0.1700
Data Index: 7024314 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.9776. Min Act: -0.1700
Data Index: 6548959 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.9776. Min Act: -0.1700
Data Index: 6317169 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.9463. Min Act: -0.1700
Data Index: 3335345 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.9151. Min Act: -0.1700
Data Index: 5181434 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.8838. Min Act: -0.1700
Data Index: 5840215 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.8526. Min Act: -0.1700
Data Index: 8589805 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.8526. Min Act: -0.1700
Data Index: 7654743 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.8526. Min Act: -0.1700
Data Index: 6766727 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.8526. Min Act: -0.1700
Data Index: 2784047 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.8526. Min Act: -0.1700
Data Index: 6214999 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.7901. Min Act: -0.1700
Data Index: 4701998 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5713. Min Range: -7.5713
Max Act: 6.7901. Min Act: -0.1700
Data Index: 1628182 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19