Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2885. Min Range: -6.2885
Max Act: 6.2885. Min Act: -0.1700
Data Index: 6868692 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2885. Min Range: -6.2885
Max Act: 6.2572. Min Act: -0.1700
Data Index: 6763582 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2885. Min Range: -6.2885
Max Act: 6.2260. Min Act: -0.1700
Data Index: 633558 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2885. Min Range: -6.2885
Max Act: 6.1947. Min Act: -0.1700
Data Index: 1601380 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2885. Min Range: -6.2885
Max Act: 6.1010. Min Act: -0.1700
Data Index: 3619065 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2885. Min Range: -6.2885
Max Act: 6.0385. Min Act: -0.1700
Data Index: 5558060 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2885. Min Range: -6.2885
Max Act: 6.0072. Min Act: -0.1700
Data Index: 8449530 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2885. Min Range: -6.2885
Max Act: 6.0072. Min Act: -0.1700
Data Index: 8459109 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2885. Min Range: -6.2885
Max Act: 6.0072. Min Act: -0.1700
Data Index: 4336166 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.9135. Min Act: -0.1700
Data Index: 8623847 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.8510. Min Act: -0.1700
Data Index: 7899293 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.8822. Min Act: -0.1700
Data Index: 5800596 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.8510. Min Act: -0.1700
Data Index: 3902235 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.8197. Min Act: -0.1700
Data Index: 7935194 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.8197. Min Act: -0.1700
Data Index: 3682260 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.7885. Min Act: -0.1700
Data Index: 6184997 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.8197. Min Act: -0.1700
Data Index: 3850310 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.8510. Min Act: -0.1700
Data Index: 1199538 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.7885. Min Act: -0.1700
Data Index: 6587587 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2885. Min Range: -6.2885
Max Act: 5.7885. Min Act: -0.1700
Data Index: 5423277 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19