Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3015 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0192. Min Range: -4.0192
Max Act: 4.0192. Min Act: -0.1700
Data Index: 5604772 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0192. Min Range: -4.0192
Max Act: 4.0192. Min Act: -0.1700
Data Index: 2394951 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.9566. Min Act: -0.1700
Data Index: 1798272 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.9566. Min Act: -0.1700
Data Index: 1131311 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.9254. Min Act: -0.1700
Data Index: 8035827 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.8941. Min Act: -0.1700
Data Index: 5357158 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.8941. Min Act: -0.1700
Data Index: 1807684 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.8628. Min Act: -0.1700
Data Index: 4898533 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.8003. Min Act: -0.1700
Data Index: 3781357 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.8003. Min Act: -0.1700
Data Index: 5372243 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.8003. Min Act: -0.1700
Data Index: 470440 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.7690. Min Act: -0.1700
Data Index: 1659475 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.7690. Min Act: -0.1700
Data Index: 1834237 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.7690. Min Act: -0.1700
Data Index: 535680 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.7534. Min Act: -0.1700
Data Index: 7826252 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.7377. Min Act: -0.1700
Data Index: 7929215 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.7690. Min Act: -0.1700
Data Index: 1074876 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.7377. Min Act: -0.1700
Data Index: 4781321 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.7377. Min Act: -0.1700
Data Index: 5583020 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0192. Min Range: -4.0192
Max Act: 3.7065. Min Act: -0.1700
Data Index: 2550267 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19