Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3869 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.4072. Min Act: -0.1699
Data Index: 7086263 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.3445. Min Act: -0.1699
Data Index: 7086264 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.2345. Min Act: -0.1700
Data Index: 7086262 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.1874. Min Act: -0.1700
Data Index: 3143030 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.1716. Min Act: -0.1700
Data Index: 1494995 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.1559. Min Act: -0.1696
Data Index: 1477643 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.1402. Min Act: -0.1700
Data Index: 2587017 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.1559. Min Act: -0.1699
Data Index: 6893957 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.1244. Min Act: -0.1700
Data Index: 5345754 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.1087. Min Act: -0.1700
Data Index: 4022559 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.1087. Min Act: -0.1700
Data Index: 3166857 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.1087. Min Act: -0.1700
Data Index: 4540156 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.0929. Min Act: -0.1700
Data Index: 7243613 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.0929. Min Act: -0.1700
Data Index: 7660300 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.0771. Min Act: -0.1695
Data Index: 1477609 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.0771. Min Act: -0.1700
Data Index: 5168689 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.0614. Min Act: -0.1700
Data Index: 1389621 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.0614. Min Act: -0.1700
Data Index: 4479097 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.0614. Min Act: -0.1700
Data Index: 197567 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4072. Min Range: -3.4072
Max Act: 3.0614. Min Act: -0.1700
Data Index: 698800 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19