Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0019. Min Range: -5.0019
Max Act: 5.0019. Min Act: -0.1700
Data Index: 5820372 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.8769. Min Act: -0.1700
Data Index: 4838086 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.7832. Min Act: -0.1700
Data Index: 6479846 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.7207. Min Act: -0.1700
Data Index: 7421704 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6894. Min Act: -0.1700
Data Index: 3618762 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6894. Min Act: -0.1700
Data Index: 8627696 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6582. Min Act: -0.1700
Data Index: 5004433 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6582. Min Act: -0.1700
Data Index: 8744232 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6269. Min Act: -0.1700
Data Index: 735647 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5957. Min Act: -0.1700
Data Index: 6370976 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.6269. Min Act: -0.1700
Data Index: 2350350 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5957. Min Act: -0.1700
Data Index: 6898679 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5644. Min Act: -0.1700
Data Index: 1992125 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5644. Min Act: -0.1700
Data Index: 8248294 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5644. Min Act: -0.1700
Data Index: 4667343 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5332. Min Act: -0.1700
Data Index: 8190371 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5332. Min Act: -0.1700
Data Index: 6801585 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5332. Min Act: -0.1700
Data Index: 4440781 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5332. Min Act: -0.1700
Data Index: 5372646 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0019. Min Range: -5.0019
Max Act: 4.5019. Min Act: -0.1700
Data Index: 8115893 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19