Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.4387. Min Act: -0.1700
Data Index: 2156101 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.2512. Min Act: -0.1700
Data Index: 3967271 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.2199. Min Act: -0.1700
Data Index: 2210548 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.1887. Min Act: -0.1700
Data Index: 663511 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.1887. Min Act: -0.1700
Data Index: 2696666 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.1574. Min Act: -0.1700
Data Index: 3018067 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.0949. Min Act: -0.1700
Data Index: 383803 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.0949. Min Act: -0.1700
Data Index: 4706519 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.0949. Min Act: -0.1700
Data Index: 4362071 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.0324. Min Act: -0.1700
Data Index: 5646216 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.0012. Min Act: -0.1700
Data Index: 7299014 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.0324. Min Act: -0.1700
Data Index: 7723503 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.0012. Min Act: -0.1700
Data Index: 7862097 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4387. Min Range: -6.4387
Max Act: 6.0012. Min Act: -0.1700
Data Index: 7747808 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4387. Min Range: -6.4387
Max Act: 5.9387. Min Act: -0.1700
Data Index: 4993201 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4387. Min Range: -6.4387
Max Act: 5.9699. Min Act: -0.1700
Data Index: 475938 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4387. Min Range: -6.4387
Max Act: 5.9699. Min Act: -0.1700
Data Index: 1273089 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4387. Min Range: -6.4387
Max Act: 5.9387. Min Act: -0.1700
Data Index: 4672926 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4387. Min Range: -6.4387
Max Act: 5.9387. Min Act: -0.1700
Data Index: 3353372 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4387. Min Range: -6.4387
Max Act: 5.9074. Min Act: -0.1700
Data Index: 1395710 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19