Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.7974. Min Act: -0.1700
Data Index: 2364082 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.7974. Min Act: -0.1700
Data Index: 3967142 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.7662. Min Act: -0.1700
Data Index: 7272510 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.7349. Min Act: -0.1700
Data Index: 1329934 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.7349. Min Act: -0.1700
Data Index: 2703012 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.5474. Min Act: -0.1700
Data Index: 621765 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.4537. Min Act: -0.1700
Data Index: 6128306 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.4224. Min Act: -0.1700
Data Index: 2305867 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.3912. Min Act: -0.1700
Data Index: 7734436 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.3912. Min Act: -0.1700
Data Index: 3752286 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.3287. Min Act: -0.1700
Data Index: 3877076 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.3287. Min Act: -0.1700
Data Index: 353026 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.2662. Min Act: -0.1700
Data Index: 4738624 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.2974. Min Act: -0.1700
Data Index: 3353528 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.2662. Min Act: -0.1700
Data Index: 1521270 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.2662. Min Act: -0.1700
Data Index: 3753588 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.2662. Min Act: -0.1700
Data Index: 6703365 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.2349. Min Act: -0.1700
Data Index: 2508007 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.2662. Min Act: -0.1700
Data Index: 2570018 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7974. Min Range: -5.7974
Max Act: 5.2037. Min Act: -0.1700
Data Index: 7412119 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19