Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 354 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2708. Min Range: -10.2708
Max Act: 10.2708. Min Act: -0.1700
Data Index: 5340925 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2708. Min Range: -10.2708
Max Act: 10.1458. Min Act: -0.1700
Data Index: 5985157 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2708. Min Range: -10.2708
Max Act: 10.0208. Min Act: -0.1700
Data Index: 137184 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.8958. Min Act: -0.1700
Data Index: 4189031 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.6458. Min Act: -0.1700
Data Index: 7081621 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.5833. Min Act: -0.1700
Data Index: 6489703 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.5833. Min Act: -0.1700
Data Index: 8170707 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.5833. Min Act: -0.1700
Data Index: 6554762 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.3958. Min Act: -0.1700
Data Index: 756805 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.3333. Min Act: -0.1700
Data Index: 7725610 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.2708. Min Act: -0.1700
Data Index: 2519925 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.3333. Min Act: -0.1700
Data Index: 6540107 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.2708. Min Act: -0.1700
Data Index: 3524578 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.3333. Min Act: -0.1700
Data Index: 1173537 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.2708. Min Act: -0.1700
Data Index: 6783609 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.2708. Min Act: -0.1700
Data Index: 6917458 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.2708. Min Act: -0.1700
Data Index: 7853194 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.2708. Min Act: -0.1700
Data Index: 5764184 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.2708. Min Act: -0.1700
Data Index: 5571118 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2708. Min Range: -10.2708
Max Act: 9.2708. Min Act: -0.1700
Data Index: 3264371 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19