Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4975 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.2648. Min Act: -0.1700
Data Index: 3621547 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.2336. Min Act: -0.1700
Data Index: 683886 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.1710. Min Act: -0.1700
Data Index: 518505 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.2023. Min Act: -0.1700
Data Index: 8497273 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.1398. Min Act: -0.1700
Data Index: 984778 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.1398. Min Act: -0.1700
Data Index: 3173308 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.1085. Min Act: -0.1700
Data Index: 3824256 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.0773. Min Act: -0.1700
Data Index: 7053280 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.1085. Min Act: -0.1700
Data Index: 8396710 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.1398. Min Act: -0.1700
Data Index: 5937331 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.1085. Min Act: -0.1700
Data Index: 7351578 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.0773. Min Act: -0.1700
Data Index: 2353560 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.1085. Min Act: -0.1700
Data Index: 6742130 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.0773. Min Act: -0.1700
Data Index: 6312989 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.0460. Min Act: -0.1700
Data Index: 6312988 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.0460. Min Act: -0.1700
Data Index: 5628118 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.0460. Min Act: -0.1700
Data Index: 8396704 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.0773. Min Act: -0.1700
Data Index: 6508773 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.0773. Min Act: -0.1700
Data Index: 3371174 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2648. Min Range: -4.2648
Max Act: 4.0148. Min Act: -0.1700
Data Index: 8060255 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19