Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0875. Min Range: -7.0875
Max Act: 7.0875. Min Act: -0.1700
Data Index: 5995116 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.9937. Min Act: -0.1700
Data Index: 1880540 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.9625. Min Act: -0.1700
Data Index: 3528514 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.9625. Min Act: -0.1700
Data Index: 6840626 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.9000. Min Act: -0.1700
Data Index: 1381329 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.9312. Min Act: -0.1700
Data Index: 1381340 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.9000. Min Act: -0.1700
Data Index: 3971456 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.9000. Min Act: -0.1700
Data Index: 6410335 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.9000. Min Act: -0.1700
Data Index: 1381333 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8687. Min Act: -0.1700
Data Index: 1381330 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8375. Min Act: -0.1700
Data Index: 1381341 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8687. Min Act: -0.1700
Data Index: 4464505 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8687. Min Act: -0.1700
Data Index: 1381336 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8687. Min Act: -0.1700
Data Index: 490507 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8687. Min Act: -0.1700
Data Index: 1381331 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8375. Min Act: -0.1700
Data Index: 4648320 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8375. Min Act: -0.1700
Data Index: 8084266 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8375. Min Act: -0.1700
Data Index: 1381332 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8062. Min Act: -0.1700
Data Index: 1381334 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0875. Min Range: -7.0875
Max Act: 6.8062. Min Act: -0.1700
Data Index: 1381339 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19