Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1022 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3018. Min Range: -4.3018
Max Act: 4.3018. Min Act: -0.1700
Data Index: 4412709 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3018. Min Range: -4.3018
Max Act: 4.0205. Min Act: -0.1700
Data Index: 6690481 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.8642. Min Act: -0.1700
Data Index: 1411265 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.8016. Min Act: -0.1700
Data Index: 408212 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.7547. Min Act: -0.1700
Data Index: 1099925 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.7703. Min Act: -0.1700
Data Index: 6495635 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.7703. Min Act: -0.1700
Data Index: 3658281 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.7391. Min Act: -0.1700
Data Index: 3897558 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.7391. Min Act: -0.1700
Data Index: 4210193 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.7391. Min Act: -0.1700
Data Index: 8313475 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.6765. Min Act: -0.1700
Data Index: 1447704 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.6452. Min Act: -0.1700
Data Index: 5983764 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.6452. Min Act: -0.1700
Data Index: 4000093 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.6452. Min Act: -0.1700
Data Index: 3865946 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.6139. Min Act: -0.1700
Data Index: 1088826 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.6139. Min Act: -0.1700
Data Index: 5367350 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.5826. Min Act: -0.1700
Data Index: 7276896 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.5513. Min Act: -0.1700
Data Index: 4291920 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.5513. Min Act: -0.1700
Data Index: 4646968 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3018. Min Range: -4.3018
Max Act: 3.5513. Min Act: -0.1700
Data Index: 2543595 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19